OpenAI: gpt-oss-120b

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B pa…

openai/gpt-oss-120b

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Specifications & capabilities

Input
text
Output
text
Context window · tokens
131072
Published model ID
gpt-oss-120b
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling
Description source ↗

Evaluations

1–20 / 1,066

Kaggle Benchmarks

100%

source id
kaggleBenchmarks
leaderboard name
GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-098
dimension
reasoning
metric
GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-098
rank
1
aggregation scope
kaggle
true
status
published
license
Apache-2.0
direction
higherIsBetter
conditions
task
id
984147
name
gpqa-diamond-zero-shot/task-098
version
1
sort_order
DESCENDING
display_type
percentages
benchmark
id
7
name
GPQA Diamond Zero‑Shot
type
INDIVIDUAL
owner
open-benchmarks
version
2
categories
  • general knowledge and reasoning
  • science
version_id
8176
maintainer_tier
Kaggle-maintained
maintenance_level
KAGGLE_MAINTAINED
candidate
candidate_class
modelVersion
record_kind
aggregate
attribution
Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
license_url
https://www.apache.org/licenses/LICENSE-2.0
metric_kind
GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-098
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
8176/leaderboard.json
source_page
https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
measurements
  • name
    gpqa-diamond-zero-shot/task-098
    unit
    percent
    scale
    1
    metric
    GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-098
    result
    resultCase
    numericResult
    booleanResult
    false
    numericResult
    value
    1
    standardDeviation
    0
    confidenceInterval
    0
    hasStandardDeviation
    false
    hasConfidenceInterval
    false
    hasUnevenConfidenceInterval
    false
    taskVersionId
    0
    evaluationDate
    2026-10-09T03:49:37.5612462Z
    hasBooleanResult
    false
    hasNumericResult
    true
    hasTaskVersionId
    false
    hasEvaluationDate
    true
    numericResultNullable
    value
    1
    standardDeviation
    0
    confidenceInterval
    0
    hasStandardDeviation
    false
    hasConfidenceInterval
    false
    hasUnevenConfidenceInterval
    false
    hasNumericResultPublic
    false
    customAdditionalResults
      hasNumericResultPrivate
      false
      task_id
      984147
      sort_order
      DESCENDING
      source_name
      gpqa-diamond-zero-shot/task-098
      display_type
      percentages
      task_version
      1
      task_display_type
      RAW_VALUES
      normalization_status
      normalized
    published_at
    2026-10-12T17:49:58.132967500Z
    candidate_class
    modelVersion
    source_revision
    b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
    publisher_anchor
    openai/gpt-oss-120b
    metric_population
    32
    benchmark_evaluation
    true
    task_metadata_source
    benchmarkVersion
    candidate_metadata_source
    benchmarkVersionMappings
    evaluated at
    2026-10-09T03:49:37.561Z
    source model id
    gpt-oss-120b
    Original result ↗

    Kaggle Benchmarks

    100%

    source id
    kaggleBenchmarks
    leaderboard name
    GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-136
    dimension
    reasoning
    metric
    GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-136
    rank
    1
    aggregation scope
    kaggle
    true
    status
    published
    license
    Apache-2.0
    direction
    higherIsBetter
    conditions
    task
    id
    984186
    name
    gpqa-diamond-zero-shot/task-136
    version
    1
    sort_order
    DESCENDING
    display_type
    percentages
    benchmark
    id
    7
    name
    GPQA Diamond Zero‑Shot
    type
    INDIVIDUAL
    owner
    open-benchmarks
    version
    2
    categories
    • general knowledge and reasoning
    • science
    version_id
    8176
    maintainer_tier
    Kaggle-maintained
    maintenance_level
    KAGGLE_MAINTAINED
    candidate
    candidate_class
    modelVersion
    record_kind
    aggregate
    attribution
    Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
    license_url
    https://www.apache.org/licenses/LICENSE-2.0
    metric_kind
    GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-136
    rank_method
    competition rank among reported evaluations in identical conditions, including unlinked observations
    source_file
    8176/leaderboard.json
    source_page
    https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
    measurements
    • name
      gpqa-diamond-zero-shot/task-136
      unit
      percent
      scale
      1
      metric
      GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-136
      result
      resultCase
      numericResult
      booleanResult
      false
      numericResult
      value
      1
      standardDeviation
      0
      confidenceInterval
      0
      hasStandardDeviation
      false
      hasConfidenceInterval
      false
      hasUnevenConfidenceInterval
      false
      taskVersionId
      0
      evaluationDate
      2026-10-09T01:32:06.7199776Z
      hasBooleanResult
      false
      hasNumericResult
      true
      hasTaskVersionId
      false
      hasEvaluationDate
      true
      numericResultNullable
      value
      1
      standardDeviation
      0
      confidenceInterval
      0
      hasStandardDeviation
      false
      hasConfidenceInterval
      false
      hasUnevenConfidenceInterval
      false
      hasNumericResultPublic
      false
      customAdditionalResults
        hasNumericResultPrivate
        false
        task_id
        984186
        sort_order
        DESCENDING
        source_name
        gpqa-diamond-zero-shot/task-136
        display_type
        percentages
        task_version
        1
        task_display_type
        RAW_VALUES
        normalization_status
        normalized
      published_at
      2026-10-12T17:49:58.132967500Z
      candidate_class
      modelVersion
      source_revision
      b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
      publisher_anchor
      openai/gpt-oss-120b
      metric_population
      32
      benchmark_evaluation
      true
      task_metadata_source
      benchmarkVersion
      candidate_metadata_source
      benchmarkVersionMappings
      evaluated at
      2026-10-09T01:32:06.719Z
      source model id
      gpt-oss-120b
      Original result ↗

      Kaggle Benchmarks

      100%

      source id
      kaggleBenchmarks
      leaderboard name
      GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-095
      dimension
      reasoning
      metric
      GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-095
      rank
      1
      aggregation scope
      kaggle
      true
      status
      published
      license
      Apache-2.0
      direction
      higherIsBetter
      conditions
      task
      id
      984144
      name
      gpqa-diamond-zero-shot/task-095
      version
      1
      sort_order
      DESCENDING
      display_type
      percentages
      benchmark
      id
      7
      name
      GPQA Diamond Zero‑Shot
      type
      INDIVIDUAL
      owner
      open-benchmarks
      version
      2
      categories
      • general knowledge and reasoning
      • science
      version_id
      8176
      maintainer_tier
      Kaggle-maintained
      maintenance_level
      KAGGLE_MAINTAINED
      candidate
      candidate_class
      modelVersion
      record_kind
      aggregate
      attribution
      Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
      license_url
      https://www.apache.org/licenses/LICENSE-2.0
      metric_kind
      GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-095
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      8176/leaderboard.json
      source_page
      https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
      measurements
      • name
        gpqa-diamond-zero-shot/task-095
        unit
        percent
        scale
        1
        metric
        GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-095
        result
        resultCase
        numericResult
        booleanResult
        false
        numericResult
        value
        1
        standardDeviation
        0
        confidenceInterval
        0
        hasStandardDeviation
        false
        hasConfidenceInterval
        false
        hasUnevenConfidenceInterval
        false
        taskVersionId
        0
        evaluationDate
        2026-10-09T03:40:37.4551367Z
        hasBooleanResult
        false
        hasNumericResult
        true
        hasTaskVersionId
        false
        hasEvaluationDate
        true
        numericResultNullable
        value
        1
        standardDeviation
        0
        confidenceInterval
        0
        hasStandardDeviation
        false
        hasConfidenceInterval
        false
        hasUnevenConfidenceInterval
        false
        hasNumericResultPublic
        false
        customAdditionalResults
          hasNumericResultPrivate
          false
          task_id
          984144
          sort_order
          DESCENDING
          source_name
          gpqa-diamond-zero-shot/task-095
          display_type
          percentages
          task_version
          1
          task_display_type
          RAW_VALUES
          normalization_status
          normalized
        published_at
        2026-10-12T17:49:58.132967500Z
        candidate_class
        modelVersion
        source_revision
        b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
        publisher_anchor
        openai/gpt-oss-120b
        metric_population
        32
        benchmark_evaluation
        true
        task_metadata_source
        benchmarkVersion
        candidate_metadata_source
        benchmarkVersionMappings
        evaluated at
        2026-10-09T03:40:37.455Z
        source model id
        gpt-oss-120b
        Original result ↗

        Kaggle Benchmarks

        100%

        source id
        kaggleBenchmarks
        leaderboard name
        GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-031
        dimension
        reasoning
        metric
        GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-031
        rank
        1
        aggregation scope
        kaggle
        true
        status
        published
        license
        Apache-2.0
        direction
        higherIsBetter
        conditions
        task
        id
        984079
        name
        gpqa-diamond-zero-shot/task-031
        version
        1
        sort_order
        DESCENDING
        display_type
        percentages
        benchmark
        id
        7
        name
        GPQA Diamond Zero‑Shot
        type
        INDIVIDUAL
        owner
        open-benchmarks
        version
        2
        categories
        • general knowledge and reasoning
        • science
        version_id
        8176
        maintainer_tier
        Kaggle-maintained
        maintenance_level
        KAGGLE_MAINTAINED
        candidate
        candidate_class
        modelVersion
        record_kind
        aggregate
        attribution
        Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
        license_url
        https://www.apache.org/licenses/LICENSE-2.0
        metric_kind
        GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-031
        rank_method
        competition rank among reported evaluations in identical conditions, including unlinked observations
        source_file
        8176/leaderboard.json
        source_page
        https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
        measurements
        • name
          gpqa-diamond-zero-shot/task-031
          unit
          percent
          scale
          1
          metric
          GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-031
          result
          resultCase
          numericResult
          booleanResult
          false
          numericResult
          value
          1
          standardDeviation
          0
          confidenceInterval
          0
          hasStandardDeviation
          false
          hasConfidenceInterval
          false
          hasUnevenConfidenceInterval
          false
          taskVersionId
          0
          evaluationDate
          2026-10-08T23:48:58.235564Z
          hasBooleanResult
          false
          hasNumericResult
          true
          hasTaskVersionId
          false
          hasEvaluationDate
          true
          numericResultNullable
          value
          1
          standardDeviation
          0
          confidenceInterval
          0
          hasStandardDeviation
          false
          hasConfidenceInterval
          false
          hasUnevenConfidenceInterval
          false
          hasNumericResultPublic
          false
          customAdditionalResults
            hasNumericResultPrivate
            false
            task_id
            984079
            sort_order
            DESCENDING
            source_name
            gpqa-diamond-zero-shot/task-031
            display_type
            percentages
            task_version
            1
            task_display_type
            RAW_VALUES
            normalization_status
            normalized
          published_at
          2026-10-12T17:49:58.132967500Z
          candidate_class
          modelVersion
          source_revision
          b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
          publisher_anchor
          openai/gpt-oss-120b
          metric_population
          32
          benchmark_evaluation
          true
          task_metadata_source
          benchmarkVersion
          candidate_metadata_source
          benchmarkVersionMappings
          evaluated at
          2026-10-08T23:48:58.235Z
          source model id
          gpt-oss-120b
          Original result ↗

          Kaggle Benchmarks

          100%

          source id
          kaggleBenchmarks
          leaderboard name
          GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-194
          dimension
          reasoning
          metric
          GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-194
          rank
          1
          aggregation scope
          kaggle
          true
          status
          published
          license
          Apache-2.0
          direction
          higherIsBetter
          conditions
          task
          id
          984244
          name
          gpqa-diamond-zero-shot/task-194
          version
          1
          sort_order
          DESCENDING
          display_type
          percentages
          benchmark
          id
          7
          name
          GPQA Diamond Zero‑Shot
          type
          INDIVIDUAL
          owner
          open-benchmarks
          version
          2
          categories
          • general knowledge and reasoning
          • science
          version_id
          8176
          maintainer_tier
          Kaggle-maintained
          maintenance_level
          KAGGLE_MAINTAINED
          candidate
          candidate_class
          modelVersion
          record_kind
          aggregate
          attribution
          Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
          license_url
          https://www.apache.org/licenses/LICENSE-2.0
          metric_kind
          GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-194
          rank_method
          competition rank among reported evaluations in identical conditions, including unlinked observations
          source_file
          8176/leaderboard.json
          source_page
          https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
          measurements
          • name
            gpqa-diamond-zero-shot/task-194
            unit
            percent
            scale
            1
            metric
            GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-194
            result
            resultCase
            numericResult
            booleanResult
            false
            numericResult
            value
            1
            standardDeviation
            0
            confidenceInterval
            0
            hasStandardDeviation
            false
            hasConfidenceInterval
            false
            hasUnevenConfidenceInterval
            false
            taskVersionId
            0
            evaluationDate
            2026-10-09T02:50:51.165407Z
            hasBooleanResult
            false
            hasNumericResult
            true
            hasTaskVersionId
            false
            hasEvaluationDate
            true
            numericResultNullable
            value
            1
            standardDeviation
            0
            confidenceInterval
            0
            hasStandardDeviation
            false
            hasConfidenceInterval
            false
            hasUnevenConfidenceInterval
            false
            hasNumericResultPublic
            false
            customAdditionalResults
              hasNumericResultPrivate
              false
              task_id
              984244
              sort_order
              DESCENDING
              source_name
              gpqa-diamond-zero-shot/task-194
              display_type
              percentages
              task_version
              1
              task_display_type
              RAW_VALUES
              normalization_status
              normalized
            published_at
            2026-10-12T17:49:58.132967500Z
            candidate_class
            modelVersion
            source_revision
            b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
            publisher_anchor
            openai/gpt-oss-120b
            metric_population
            32
            benchmark_evaluation
            true
            task_metadata_source
            benchmarkVersion
            candidate_metadata_source
            benchmarkVersionMappings
            evaluated at
            2026-10-09T02:50:51.165Z
            source model id
            gpt-oss-120b
            Original result ↗

            Kaggle Benchmarks

            100%

            source id
            kaggleBenchmarks
            leaderboard name
            GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-091
            dimension
            reasoning
            metric
            GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-091
            rank
            1
            aggregation scope
            kaggle
            true
            status
            published
            license
            Apache-2.0
            direction
            higherIsBetter
            conditions
            task
            id
            984140
            name
            gpqa-diamond-zero-shot/task-091
            version
            1
            sort_order
            DESCENDING
            display_type
            percentages
            benchmark
            id
            7
            name
            GPQA Diamond Zero‑Shot
            type
            INDIVIDUAL
            owner
            open-benchmarks
            version
            2
            categories
            • general knowledge and reasoning
            • science
            version_id
            8176
            maintainer_tier
            Kaggle-maintained
            maintenance_level
            KAGGLE_MAINTAINED
            candidate
            candidate_class
            modelVersion
            record_kind
            aggregate
            attribution
            Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
            license_url
            https://www.apache.org/licenses/LICENSE-2.0
            metric_kind
            GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-091
            rank_method
            competition rank among reported evaluations in identical conditions, including unlinked observations
            source_file
            8176/leaderboard.json
            source_page
            https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
            measurements
            • name
              gpqa-diamond-zero-shot/task-091
              unit
              percent
              scale
              1
              metric
              GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-091
              result
              resultCase
              numericResult
              booleanResult
              false
              numericResult
              value
              1
              standardDeviation
              0
              confidenceInterval
              0
              hasStandardDeviation
              false
              hasConfidenceInterval
              false
              hasUnevenConfidenceInterval
              false
              taskVersionId
              0
              evaluationDate
              2026-10-09T00:25:12.1415242Z
              hasBooleanResult
              false
              hasNumericResult
              true
              hasTaskVersionId
              false
              hasEvaluationDate
              true
              numericResultNullable
              value
              1
              standardDeviation
              0
              confidenceInterval
              0
              hasStandardDeviation
              false
              hasConfidenceInterval
              false
              hasUnevenConfidenceInterval
              false
              hasNumericResultPublic
              false
              customAdditionalResults
                hasNumericResultPrivate
                false
                task_id
                984140
                sort_order
                DESCENDING
                source_name
                gpqa-diamond-zero-shot/task-091
                display_type
                percentages
                task_version
                1
                task_display_type
                RAW_VALUES
                normalization_status
                normalized
              published_at
              2026-10-12T17:49:58.132967500Z
              candidate_class
              modelVersion
              source_revision
              b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
              publisher_anchor
              openai/gpt-oss-120b
              metric_population
              32
              benchmark_evaluation
              true
              task_metadata_source
              benchmarkVersion
              candidate_metadata_source
              benchmarkVersionMappings
              evaluated at
              2026-10-09T00:25:12.141Z
              source model id
              gpt-oss-120b
              Original result ↗

              Kaggle Benchmarks

              100%

              source id
              kaggleBenchmarks
              leaderboard name
              GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-059
              dimension
              reasoning
              metric
              GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-059
              rank
              1
              aggregation scope
              kaggle
              true
              status
              published
              license
              Apache-2.0
              direction
              higherIsBetter
              conditions
              task
              id
              984108
              name
              gpqa-diamond-zero-shot/task-059
              version
              1
              sort_order
              DESCENDING
              display_type
              percentages
              benchmark
              id
              7
              name
              GPQA Diamond Zero‑Shot
              type
              INDIVIDUAL
              owner
              open-benchmarks
              version
              2
              categories
              • general knowledge and reasoning
              • science
              version_id
              8176
              maintainer_tier
              Kaggle-maintained
              maintenance_level
              KAGGLE_MAINTAINED
              candidate
              candidate_class
              modelVersion
              record_kind
              aggregate
              attribution
              Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
              license_url
              https://www.apache.org/licenses/LICENSE-2.0
              metric_kind
              GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-059
              rank_method
              competition rank among reported evaluations in identical conditions, including unlinked observations
              source_file
              8176/leaderboard.json
              source_page
              https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
              measurements
              • name
                gpqa-diamond-zero-shot/task-059
                unit
                percent
                scale
                1
                metric
                GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-059
                result
                resultCase
                numericResult
                booleanResult
                false
                numericResult
                value
                1
                standardDeviation
                0
                confidenceInterval
                0
                hasStandardDeviation
                false
                hasConfidenceInterval
                false
                hasUnevenConfidenceInterval
                false
                taskVersionId
                0
                evaluationDate
                2026-10-09T03:12:19.5801289Z
                hasBooleanResult
                false
                hasNumericResult
                true
                hasTaskVersionId
                false
                hasEvaluationDate
                true
                numericResultNullable
                value
                1
                standardDeviation
                0
                confidenceInterval
                0
                hasStandardDeviation
                false
                hasConfidenceInterval
                false
                hasUnevenConfidenceInterval
                false
                hasNumericResultPublic
                false
                customAdditionalResults
                  hasNumericResultPrivate
                  false
                  task_id
                  984108
                  sort_order
                  DESCENDING
                  source_name
                  gpqa-diamond-zero-shot/task-059
                  display_type
                  percentages
                  task_version
                  1
                  task_display_type
                  RAW_VALUES
                  normalization_status
                  normalized
                published_at
                2026-10-12T17:49:58.132967500Z
                candidate_class
                modelVersion
                source_revision
                b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                publisher_anchor
                openai/gpt-oss-120b
                metric_population
                32
                benchmark_evaluation
                true
                task_metadata_source
                benchmarkVersion
                candidate_metadata_source
                benchmarkVersionMappings
                evaluated at
                2026-10-09T03:12:19.580Z
                source model id
                gpt-oss-120b
                Original result ↗

                Kaggle Benchmarks

                100%

                source id
                kaggleBenchmarks
                leaderboard name
                GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-041
                dimension
                reasoning
                metric
                GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-041
                rank
                1
                aggregation scope
                kaggle
                true
                status
                published
                license
                Apache-2.0
                direction
                higherIsBetter
                conditions
                task
                id
                984089
                name
                gpqa-diamond-zero-shot/task-041
                version
                1
                sort_order
                DESCENDING
                display_type
                percentages
                benchmark
                id
                7
                name
                GPQA Diamond Zero‑Shot
                type
                INDIVIDUAL
                owner
                open-benchmarks
                version
                2
                categories
                • general knowledge and reasoning
                • science
                version_id
                8176
                maintainer_tier
                Kaggle-maintained
                maintenance_level
                KAGGLE_MAINTAINED
                candidate
                candidate_class
                modelVersion
                record_kind
                aggregate
                attribution
                Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                license_url
                https://www.apache.org/licenses/LICENSE-2.0
                metric_kind
                GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-041
                rank_method
                competition rank among reported evaluations in identical conditions, including unlinked observations
                source_file
                8176/leaderboard.json
                source_page
                https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                measurements
                • name
                  gpqa-diamond-zero-shot/task-041
                  unit
                  percent
                  scale
                  1
                  metric
                  GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-041
                  result
                  resultCase
                  numericResult
                  booleanResult
                  false
                  numericResult
                  value
                  1
                  standardDeviation
                  0
                  confidenceInterval
                  0
                  hasStandardDeviation
                  false
                  hasConfidenceInterval
                  false
                  hasUnevenConfidenceInterval
                  false
                  taskVersionId
                  0
                  evaluationDate
                  2026-10-08T23:56:53.415797Z
                  hasBooleanResult
                  false
                  hasNumericResult
                  true
                  hasTaskVersionId
                  false
                  hasEvaluationDate
                  true
                  numericResultNullable
                  value
                  1
                  standardDeviation
                  0
                  confidenceInterval
                  0
                  hasStandardDeviation
                  false
                  hasConfidenceInterval
                  false
                  hasUnevenConfidenceInterval
                  false
                  hasNumericResultPublic
                  false
                  customAdditionalResults
                    hasNumericResultPrivate
                    false
                    task_id
                    984089
                    sort_order
                    DESCENDING
                    source_name
                    gpqa-diamond-zero-shot/task-041
                    display_type
                    percentages
                    task_version
                    1
                    task_display_type
                    RAW_VALUES
                    normalization_status
                    normalized
                  published_at
                  2026-10-12T17:49:58.132967500Z
                  candidate_class
                  modelVersion
                  source_revision
                  b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                  publisher_anchor
                  openai/gpt-oss-120b
                  metric_population
                  32
                  benchmark_evaluation
                  true
                  task_metadata_source
                  benchmarkVersion
                  candidate_metadata_source
                  benchmarkVersionMappings
                  evaluated at
                  2026-10-08T23:56:53.415Z
                  source model id
                  gpt-oss-120b
                  Original result ↗

                  Kaggle Benchmarks

                  100%

                  source id
                  kaggleBenchmarks
                  leaderboard name
                  GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-107
                  dimension
                  reasoning
                  metric
                  GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-107
                  rank
                  1
                  aggregation scope
                  kaggle
                  true
                  status
                  published
                  license
                  Apache-2.0
                  direction
                  higherIsBetter
                  conditions
                  task
                  id
                  984156
                  name
                  gpqa-diamond-zero-shot/task-107
                  version
                  1
                  sort_order
                  DESCENDING
                  display_type
                  percentages
                  benchmark
                  id
                  7
                  name
                  GPQA Diamond Zero‑Shot
                  type
                  INDIVIDUAL
                  owner
                  open-benchmarks
                  version
                  2
                  categories
                  • general knowledge and reasoning
                  • science
                  version_id
                  8176
                  maintainer_tier
                  Kaggle-maintained
                  maintenance_level
                  KAGGLE_MAINTAINED
                  candidate
                  candidate_class
                  modelVersion
                  record_kind
                  aggregate
                  attribution
                  Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                  license_url
                  https://www.apache.org/licenses/LICENSE-2.0
                  metric_kind
                  GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-107
                  rank_method
                  competition rank among reported evaluations in identical conditions, including unlinked observations
                  source_file
                  8176/leaderboard.json
                  source_page
                  https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                  measurements
                  • name
                    gpqa-diamond-zero-shot/task-107
                    unit
                    percent
                    scale
                    1
                    metric
                    GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-107
                    result
                    resultCase
                    numericResult
                    booleanResult
                    false
                    numericResult
                    value
                    1
                    standardDeviation
                    0
                    confidenceInterval
                    0
                    hasStandardDeviation
                    false
                    hasConfidenceInterval
                    false
                    hasUnevenConfidenceInterval
                    false
                    taskVersionId
                    0
                    evaluationDate
                    2026-10-09T00:32:35.0127014Z
                    hasBooleanResult
                    false
                    hasNumericResult
                    true
                    hasTaskVersionId
                    false
                    hasEvaluationDate
                    true
                    numericResultNullable
                    value
                    1
                    standardDeviation
                    0
                    confidenceInterval
                    0
                    hasStandardDeviation
                    false
                    hasConfidenceInterval
                    false
                    hasUnevenConfidenceInterval
                    false
                    hasNumericResultPublic
                    false
                    customAdditionalResults
                      hasNumericResultPrivate
                      false
                      task_id
                      984156
                      sort_order
                      DESCENDING
                      source_name
                      gpqa-diamond-zero-shot/task-107
                      display_type
                      percentages
                      task_version
                      1
                      task_display_type
                      RAW_VALUES
                      normalization_status
                      normalized
                    published_at
                    2026-10-12T17:49:58.132967500Z
                    candidate_class
                    modelVersion
                    source_revision
                    b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                    publisher_anchor
                    openai/gpt-oss-120b
                    metric_population
                    32
                    benchmark_evaluation
                    true
                    task_metadata_source
                    benchmarkVersion
                    candidate_metadata_source
                    benchmarkVersionMappings
                    evaluated at
                    2026-10-09T00:32:35.012Z
                    source model id
                    gpt-oss-120b
                    Original result ↗

                    Kaggle Benchmarks

                    100%

                    source id
                    kaggleBenchmarks
                    leaderboard name
                    GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-143
                    dimension
                    reasoning
                    metric
                    GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-143
                    rank
                    1
                    aggregation scope
                    kaggle
                    true
                    status
                    published
                    license
                    Apache-2.0
                    direction
                    higherIsBetter
                    conditions
                    task
                    id
                    984193
                    name
                    gpqa-diamond-zero-shot/task-143
                    version
                    1
                    sort_order
                    DESCENDING
                    display_type
                    percentages
                    benchmark
                    id
                    7
                    name
                    GPQA Diamond Zero‑Shot
                    type
                    INDIVIDUAL
                    owner
                    open-benchmarks
                    version
                    2
                    categories
                    • general knowledge and reasoning
                    • science
                    version_id
                    8176
                    maintainer_tier
                    Kaggle-maintained
                    maintenance_level
                    KAGGLE_MAINTAINED
                    candidate
                    candidate_class
                    modelVersion
                    record_kind
                    aggregate
                    attribution
                    Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                    license_url
                    https://www.apache.org/licenses/LICENSE-2.0
                    metric_kind
                    GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-143
                    rank_method
                    competition rank among reported evaluations in identical conditions, including unlinked observations
                    source_file
                    8176/leaderboard.json
                    source_page
                    https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                    measurements
                    • name
                      gpqa-diamond-zero-shot/task-143
                      unit
                      percent
                      scale
                      1
                      metric
                      GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-143
                      result
                      resultCase
                      numericResult
                      booleanResult
                      false
                      numericResult
                      value
                      1
                      standardDeviation
                      0
                      confidenceInterval
                      0
                      hasStandardDeviation
                      false
                      hasConfidenceInterval
                      false
                      hasUnevenConfidenceInterval
                      false
                      taskVersionId
                      0
                      evaluationDate
                      2026-10-09T01:38:47.5999173Z
                      hasBooleanResult
                      false
                      hasNumericResult
                      true
                      hasTaskVersionId
                      false
                      hasEvaluationDate
                      true
                      numericResultNullable
                      value
                      1
                      standardDeviation
                      0
                      confidenceInterval
                      0
                      hasStandardDeviation
                      false
                      hasConfidenceInterval
                      false
                      hasUnevenConfidenceInterval
                      false
                      hasNumericResultPublic
                      false
                      customAdditionalResults
                        hasNumericResultPrivate
                        false
                        task_id
                        984193
                        sort_order
                        DESCENDING
                        source_name
                        gpqa-diamond-zero-shot/task-143
                        display_type
                        percentages
                        task_version
                        1
                        task_display_type
                        RAW_VALUES
                        normalization_status
                        normalized
                      published_at
                      2026-10-12T17:49:58.132967500Z
                      candidate_class
                      modelVersion
                      source_revision
                      b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                      publisher_anchor
                      openai/gpt-oss-120b
                      metric_population
                      32
                      benchmark_evaluation
                      true
                      task_metadata_source
                      benchmarkVersion
                      candidate_metadata_source
                      benchmarkVersionMappings
                      evaluated at
                      2026-10-09T01:38:47.599Z
                      source model id
                      gpt-oss-120b
                      Original result ↗

                      Kaggle Benchmarks

                      100%

                      source id
                      kaggleBenchmarks
                      leaderboard name
                      GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-189
                      dimension
                      reasoning
                      metric
                      GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-189
                      rank
                      1
                      aggregation scope
                      kaggle
                      true
                      status
                      published
                      license
                      Apache-2.0
                      direction
                      higherIsBetter
                      conditions
                      task
                      id
                      984239
                      name
                      gpqa-diamond-zero-shot/task-189
                      version
                      1
                      sort_order
                      DESCENDING
                      display_type
                      percentages
                      benchmark
                      id
                      7
                      name
                      GPQA Diamond Zero‑Shot
                      type
                      INDIVIDUAL
                      owner
                      open-benchmarks
                      version
                      2
                      categories
                      • general knowledge and reasoning
                      • science
                      version_id
                      8176
                      maintainer_tier
                      Kaggle-maintained
                      maintenance_level
                      KAGGLE_MAINTAINED
                      candidate
                      candidate_class
                      modelVersion
                      record_kind
                      aggregate
                      attribution
                      Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                      license_url
                      https://www.apache.org/licenses/LICENSE-2.0
                      metric_kind
                      GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-189
                      rank_method
                      competition rank among reported evaluations in identical conditions, including unlinked observations
                      source_file
                      8176/leaderboard.json
                      source_page
                      https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                      measurements
                      • name
                        gpqa-diamond-zero-shot/task-189
                        unit
                        percent
                        scale
                        1
                        metric
                        GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-189
                        result
                        resultCase
                        numericResult
                        booleanResult
                        false
                        numericResult
                        value
                        1
                        standardDeviation
                        0
                        confidenceInterval
                        0
                        hasStandardDeviation
                        false
                        hasConfidenceInterval
                        false
                        hasUnevenConfidenceInterval
                        false
                        taskVersionId
                        0
                        evaluationDate
                        2026-10-09T02:43:42.1170678Z
                        hasBooleanResult
                        false
                        hasNumericResult
                        true
                        hasTaskVersionId
                        false
                        hasEvaluationDate
                        true
                        numericResultNullable
                        value
                        1
                        standardDeviation
                        0
                        confidenceInterval
                        0
                        hasStandardDeviation
                        false
                        hasConfidenceInterval
                        false
                        hasUnevenConfidenceInterval
                        false
                        hasNumericResultPublic
                        false
                        customAdditionalResults
                          hasNumericResultPrivate
                          false
                          task_id
                          984239
                          sort_order
                          DESCENDING
                          source_name
                          gpqa-diamond-zero-shot/task-189
                          display_type
                          percentages
                          task_version
                          1
                          task_display_type
                          RAW_VALUES
                          normalization_status
                          normalized
                        published_at
                        2026-10-12T17:49:58.132967500Z
                        candidate_class
                        modelVersion
                        source_revision
                        b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                        publisher_anchor
                        openai/gpt-oss-120b
                        metric_population
                        32
                        benchmark_evaluation
                        true
                        task_metadata_source
                        benchmarkVersion
                        candidate_metadata_source
                        benchmarkVersionMappings
                        evaluated at
                        2026-10-09T02:43:42.117Z
                        source model id
                        gpt-oss-120b
                        Original result ↗

                        Kaggle Benchmarks

                        100%

                        source id
                        kaggleBenchmarks
                        leaderboard name
                        GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-151
                        dimension
                        reasoning
                        metric
                        GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-151
                        rank
                        1
                        aggregation scope
                        kaggle
                        true
                        status
                        published
                        license
                        Apache-2.0
                        direction
                        higherIsBetter
                        conditions
                        task
                        id
                        984201
                        name
                        gpqa-diamond-zero-shot/task-151
                        version
                        1
                        sort_order
                        DESCENDING
                        display_type
                        percentages
                        benchmark
                        id
                        7
                        name
                        GPQA Diamond Zero‑Shot
                        type
                        INDIVIDUAL
                        owner
                        open-benchmarks
                        version
                        2
                        categories
                        • general knowledge and reasoning
                        • science
                        version_id
                        8176
                        maintainer_tier
                        Kaggle-maintained
                        maintenance_level
                        KAGGLE_MAINTAINED
                        candidate
                        candidate_class
                        modelVersion
                        record_kind
                        aggregate
                        attribution
                        Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                        license_url
                        https://www.apache.org/licenses/LICENSE-2.0
                        metric_kind
                        GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-151
                        rank_method
                        competition rank among reported evaluations in identical conditions, including unlinked observations
                        source_file
                        8176/leaderboard.json
                        source_page
                        https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                        measurements
                        • name
                          gpqa-diamond-zero-shot/task-151
                          unit
                          percent
                          scale
                          1
                          metric
                          GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-151
                          result
                          resultCase
                          numericResult
                          booleanResult
                          false
                          numericResult
                          value
                          1
                          standardDeviation
                          0
                          confidenceInterval
                          0
                          hasStandardDeviation
                          false
                          hasConfidenceInterval
                          false
                          hasUnevenConfidenceInterval
                          false
                          taskVersionId
                          0
                          evaluationDate
                          2026-10-09T01:50:35.0968651Z
                          hasBooleanResult
                          false
                          hasNumericResult
                          true
                          hasTaskVersionId
                          false
                          hasEvaluationDate
                          true
                          numericResultNullable
                          value
                          1
                          standardDeviation
                          0
                          confidenceInterval
                          0
                          hasStandardDeviation
                          false
                          hasConfidenceInterval
                          false
                          hasUnevenConfidenceInterval
                          false
                          hasNumericResultPublic
                          false
                          customAdditionalResults
                            hasNumericResultPrivate
                            false
                            task_id
                            984201
                            sort_order
                            DESCENDING
                            source_name
                            gpqa-diamond-zero-shot/task-151
                            display_type
                            percentages
                            task_version
                            1
                            task_display_type
                            RAW_VALUES
                            normalization_status
                            normalized
                          published_at
                          2026-10-12T17:49:58.132967500Z
                          candidate_class
                          modelVersion
                          source_revision
                          b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                          publisher_anchor
                          openai/gpt-oss-120b
                          metric_population
                          32
                          benchmark_evaluation
                          true
                          task_metadata_source
                          benchmarkVersion
                          candidate_metadata_source
                          benchmarkVersionMappings
                          evaluated at
                          2026-10-09T01:50:35.096Z
                          source model id
                          gpt-oss-120b
                          Original result ↗

                          Kaggle Benchmarks

                          100%

                          source id
                          kaggleBenchmarks
                          leaderboard name
                          GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-119
                          dimension
                          reasoning
                          metric
                          GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-119
                          rank
                          1
                          aggregation scope
                          kaggle
                          true
                          status
                          published
                          license
                          Apache-2.0
                          direction
                          higherIsBetter
                          conditions
                          task
                          id
                          984168
                          name
                          gpqa-diamond-zero-shot/task-119
                          version
                          1
                          sort_order
                          DESCENDING
                          display_type
                          percentages
                          benchmark
                          id
                          7
                          name
                          GPQA Diamond Zero‑Shot
                          type
                          INDIVIDUAL
                          owner
                          open-benchmarks
                          version
                          2
                          categories
                          • general knowledge and reasoning
                          • science
                          version_id
                          8176
                          maintainer_tier
                          Kaggle-maintained
                          maintenance_level
                          KAGGLE_MAINTAINED
                          candidate
                          candidate_class
                          modelVersion
                          record_kind
                          aggregate
                          attribution
                          Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                          license_url
                          https://www.apache.org/licenses/LICENSE-2.0
                          metric_kind
                          GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-119
                          rank_method
                          competition rank among reported evaluations in identical conditions, including unlinked observations
                          source_file
                          8176/leaderboard.json
                          source_page
                          https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                          measurements
                          • name
                            gpqa-diamond-zero-shot/task-119
                            unit
                            percent
                            scale
                            1
                            metric
                            GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-119
                            result
                            resultCase
                            numericResult
                            booleanResult
                            false
                            numericResult
                            value
                            1
                            standardDeviation
                            0
                            confidenceInterval
                            0
                            hasStandardDeviation
                            false
                            hasConfidenceInterval
                            false
                            hasUnevenConfidenceInterval
                            false
                            taskVersionId
                            0
                            evaluationDate
                            2026-10-09T00:38:15.4333943Z
                            hasBooleanResult
                            false
                            hasNumericResult
                            true
                            hasTaskVersionId
                            false
                            hasEvaluationDate
                            true
                            numericResultNullable
                            value
                            1
                            standardDeviation
                            0
                            confidenceInterval
                            0
                            hasStandardDeviation
                            false
                            hasConfidenceInterval
                            false
                            hasUnevenConfidenceInterval
                            false
                            hasNumericResultPublic
                            false
                            customAdditionalResults
                              hasNumericResultPrivate
                              false
                              task_id
                              984168
                              sort_order
                              DESCENDING
                              source_name
                              gpqa-diamond-zero-shot/task-119
                              display_type
                              percentages
                              task_version
                              1
                              task_display_type
                              RAW_VALUES
                              normalization_status
                              normalized
                            published_at
                            2026-10-12T17:49:58.132967500Z
                            candidate_class
                            modelVersion
                            source_revision
                            b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                            publisher_anchor
                            openai/gpt-oss-120b
                            metric_population
                            32
                            benchmark_evaluation
                            true
                            task_metadata_source
                            benchmarkVersion
                            candidate_metadata_source
                            benchmarkVersionMappings
                            evaluated at
                            2026-10-09T00:38:15.433Z
                            source model id
                            gpt-oss-120b
                            Original result ↗

                            Kaggle Benchmarks

                            100%

                            source id
                            kaggleBenchmarks
                            leaderboard name
                            GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-003
                            dimension
                            reasoning
                            metric
                            GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-003
                            rank
                            1
                            aggregation scope
                            kaggle
                            true
                            status
                            published
                            license
                            Apache-2.0
                            direction
                            higherIsBetter
                            conditions
                            task
                            id
                            984051
                            name
                            gpqa-diamond-zero-shot/task-003
                            version
                            1
                            sort_order
                            DESCENDING
                            display_type
                            percentages
                            benchmark
                            id
                            7
                            name
                            GPQA Diamond Zero‑Shot
                            type
                            INDIVIDUAL
                            owner
                            open-benchmarks
                            version
                            2
                            categories
                            • general knowledge and reasoning
                            • science
                            version_id
                            8176
                            maintainer_tier
                            Kaggle-maintained
                            maintenance_level
                            KAGGLE_MAINTAINED
                            candidate
                            candidate_class
                            modelVersion
                            record_kind
                            aggregate
                            attribution
                            Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                            license_url
                            https://www.apache.org/licenses/LICENSE-2.0
                            metric_kind
                            GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-003
                            rank_method
                            competition rank among reported evaluations in identical conditions, including unlinked observations
                            source_file
                            8176/leaderboard.json
                            source_page
                            https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                            measurements
                            • name
                              gpqa-diamond-zero-shot/task-003
                              unit
                              percent
                              scale
                              1
                              metric
                              GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-003
                              result
                              resultCase
                              numericResult
                              booleanResult
                              false
                              numericResult
                              value
                              1
                              standardDeviation
                              0
                              confidenceInterval
                              0
                              hasStandardDeviation
                              false
                              hasConfidenceInterval
                              false
                              hasUnevenConfidenceInterval
                              false
                              taskVersionId
                              0
                              evaluationDate
                              2026-10-08T23:26:15.0247719Z
                              hasBooleanResult
                              false
                              hasNumericResult
                              true
                              hasTaskVersionId
                              false
                              hasEvaluationDate
                              true
                              numericResultNullable
                              value
                              1
                              standardDeviation
                              0
                              confidenceInterval
                              0
                              hasStandardDeviation
                              false
                              hasConfidenceInterval
                              false
                              hasUnevenConfidenceInterval
                              false
                              hasNumericResultPublic
                              false
                              customAdditionalResults
                                hasNumericResultPrivate
                                false
                                task_id
                                984051
                                sort_order
                                DESCENDING
                                source_name
                                gpqa-diamond-zero-shot/task-003
                                display_type
                                percentages
                                task_version
                                1
                                task_display_type
                                RAW_VALUES
                                normalization_status
                                normalized
                              published_at
                              2026-10-12T17:49:58.132967500Z
                              candidate_class
                              modelVersion
                              source_revision
                              b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                              publisher_anchor
                              openai/gpt-oss-120b
                              metric_population
                              32
                              benchmark_evaluation
                              true
                              task_metadata_source
                              benchmarkVersion
                              candidate_metadata_source
                              benchmarkVersionMappings
                              evaluated at
                              2026-10-08T23:26:15.024Z
                              source model id
                              gpt-oss-120b
                              Original result ↗

                              Kaggle Benchmarks

                              100%

                              source id
                              kaggleBenchmarks
                              leaderboard name
                              GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-146
                              dimension
                              reasoning
                              metric
                              GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-146
                              rank
                              1
                              aggregation scope
                              kaggle
                              true
                              status
                              published
                              license
                              Apache-2.0
                              direction
                              higherIsBetter
                              conditions
                              task
                              id
                              984196
                              name
                              gpqa-diamond-zero-shot/task-146
                              version
                              1
                              sort_order
                              DESCENDING
                              display_type
                              percentages
                              benchmark
                              id
                              7
                              name
                              GPQA Diamond Zero‑Shot
                              type
                              INDIVIDUAL
                              owner
                              open-benchmarks
                              version
                              2
                              categories
                              • general knowledge and reasoning
                              • science
                              version_id
                              8176
                              maintainer_tier
                              Kaggle-maintained
                              maintenance_level
                              KAGGLE_MAINTAINED
                              candidate
                              candidate_class
                              modelVersion
                              record_kind
                              aggregate
                              attribution
                              Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                              license_url
                              https://www.apache.org/licenses/LICENSE-2.0
                              metric_kind
                              GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-146
                              rank_method
                              competition rank among reported evaluations in identical conditions, including unlinked observations
                              source_file
                              8176/leaderboard.json
                              source_page
                              https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                              measurements
                              • name
                                gpqa-diamond-zero-shot/task-146
                                unit
                                percent
                                scale
                                1
                                metric
                                GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-146
                                result
                                resultCase
                                numericResult
                                booleanResult
                                false
                                numericResult
                                value
                                1
                                standardDeviation
                                0
                                confidenceInterval
                                0
                                hasStandardDeviation
                                false
                                hasConfidenceInterval
                                false
                                hasUnevenConfidenceInterval
                                false
                                taskVersionId
                                0
                                evaluationDate
                                2026-10-09T01:44:41.0133189Z
                                hasBooleanResult
                                false
                                hasNumericResult
                                true
                                hasTaskVersionId
                                false
                                hasEvaluationDate
                                true
                                numericResultNullable
                                value
                                1
                                standardDeviation
                                0
                                confidenceInterval
                                0
                                hasStandardDeviation
                                false
                                hasConfidenceInterval
                                false
                                hasUnevenConfidenceInterval
                                false
                                hasNumericResultPublic
                                false
                                customAdditionalResults
                                  hasNumericResultPrivate
                                  false
                                  task_id
                                  984196
                                  sort_order
                                  DESCENDING
                                  source_name
                                  gpqa-diamond-zero-shot/task-146
                                  display_type
                                  percentages
                                  task_version
                                  1
                                  task_display_type
                                  RAW_VALUES
                                  normalization_status
                                  normalized
                                published_at
                                2026-10-12T17:49:58.132967500Z
                                candidate_class
                                modelVersion
                                source_revision
                                b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                publisher_anchor
                                openai/gpt-oss-120b
                                metric_population
                                32
                                benchmark_evaluation
                                true
                                task_metadata_source
                                benchmarkVersion
                                candidate_metadata_source
                                benchmarkVersionMappings
                                evaluated at
                                2026-10-09T01:44:41.013Z
                                source model id
                                gpt-oss-120b
                                Original result ↗

                                Kaggle Benchmarks

                                100%

                                source id
                                kaggleBenchmarks
                                leaderboard name
                                GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-152
                                dimension
                                reasoning
                                metric
                                GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-152
                                rank
                                1
                                aggregation scope
                                kaggle
                                true
                                status
                                published
                                license
                                Apache-2.0
                                direction
                                higherIsBetter
                                conditions
                                task
                                id
                                984202
                                name
                                gpqa-diamond-zero-shot/task-152
                                version
                                1
                                sort_order
                                DESCENDING
                                display_type
                                percentages
                                benchmark
                                id
                                7
                                name
                                GPQA Diamond Zero‑Shot
                                type
                                INDIVIDUAL
                                owner
                                open-benchmarks
                                version
                                2
                                categories
                                • general knowledge and reasoning
                                • science
                                version_id
                                8176
                                maintainer_tier
                                Kaggle-maintained
                                maintenance_level
                                KAGGLE_MAINTAINED
                                candidate
                                candidate_class
                                modelVersion
                                record_kind
                                aggregate
                                attribution
                                Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                                license_url
                                https://www.apache.org/licenses/LICENSE-2.0
                                metric_kind
                                GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-152
                                rank_method
                                competition rank among reported evaluations in identical conditions, including unlinked observations
                                source_file
                                8176/leaderboard.json
                                source_page
                                https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                                measurements
                                • name
                                  gpqa-diamond-zero-shot/task-152
                                  unit
                                  percent
                                  scale
                                  1
                                  metric
                                  GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-152
                                  result
                                  resultCase
                                  numericResult
                                  booleanResult
                                  false
                                  numericResult
                                  value
                                  1
                                  standardDeviation
                                  0
                                  confidenceInterval
                                  0
                                  hasStandardDeviation
                                  false
                                  hasConfidenceInterval
                                  false
                                  hasUnevenConfidenceInterval
                                  false
                                  taskVersionId
                                  0
                                  evaluationDate
                                  2026-10-09T01:51:45.4484696Z
                                  hasBooleanResult
                                  false
                                  hasNumericResult
                                  true
                                  hasTaskVersionId
                                  false
                                  hasEvaluationDate
                                  true
                                  numericResultNullable
                                  value
                                  1
                                  standardDeviation
                                  0
                                  confidenceInterval
                                  0
                                  hasStandardDeviation
                                  false
                                  hasConfidenceInterval
                                  false
                                  hasUnevenConfidenceInterval
                                  false
                                  hasNumericResultPublic
                                  false
                                  customAdditionalResults
                                    hasNumericResultPrivate
                                    false
                                    task_id
                                    984202
                                    sort_order
                                    DESCENDING
                                    source_name
                                    gpqa-diamond-zero-shot/task-152
                                    display_type
                                    percentages
                                    task_version
                                    1
                                    task_display_type
                                    RAW_VALUES
                                    normalization_status
                                    normalized
                                  published_at
                                  2026-10-12T17:49:58.132967500Z
                                  candidate_class
                                  modelVersion
                                  source_revision
                                  b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                  publisher_anchor
                                  openai/gpt-oss-120b
                                  metric_population
                                  32
                                  benchmark_evaluation
                                  true
                                  task_metadata_source
                                  benchmarkVersion
                                  candidate_metadata_source
                                  benchmarkVersionMappings
                                  evaluated at
                                  2026-10-09T01:51:45.448Z
                                  source model id
                                  gpt-oss-120b
                                  Original result ↗

                                  Kaggle Benchmarks

                                  100%

                                  source id
                                  kaggleBenchmarks
                                  leaderboard name
                                  GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-056
                                  dimension
                                  reasoning
                                  metric
                                  GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-056
                                  rank
                                  1
                                  aggregation scope
                                  kaggle
                                  true
                                  status
                                  published
                                  license
                                  Apache-2.0
                                  direction
                                  higherIsBetter
                                  conditions
                                  task
                                  id
                                  984105
                                  name
                                  gpqa-diamond-zero-shot/task-056
                                  version
                                  1
                                  sort_order
                                  DESCENDING
                                  display_type
                                  percentages
                                  benchmark
                                  id
                                  7
                                  name
                                  GPQA Diamond Zero‑Shot
                                  type
                                  INDIVIDUAL
                                  owner
                                  open-benchmarks
                                  version
                                  2
                                  categories
                                  • general knowledge and reasoning
                                  • science
                                  version_id
                                  8176
                                  maintainer_tier
                                  Kaggle-maintained
                                  maintenance_level
                                  KAGGLE_MAINTAINED
                                  candidate
                                  candidate_class
                                  modelVersion
                                  record_kind
                                  aggregate
                                  attribution
                                  Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                                  license_url
                                  https://www.apache.org/licenses/LICENSE-2.0
                                  metric_kind
                                  GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-056
                                  rank_method
                                  competition rank among reported evaluations in identical conditions, including unlinked observations
                                  source_file
                                  8176/leaderboard.json
                                  source_page
                                  https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                                  measurements
                                  • name
                                    gpqa-diamond-zero-shot/task-056
                                    unit
                                    percent
                                    scale
                                    1
                                    metric
                                    GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-056
                                    result
                                    resultCase
                                    numericResult
                                    booleanResult
                                    false
                                    numericResult
                                    value
                                    1
                                    standardDeviation
                                    0
                                    confidenceInterval
                                    0
                                    hasStandardDeviation
                                    false
                                    hasConfidenceInterval
                                    false
                                    hasUnevenConfidenceInterval
                                    false
                                    taskVersionId
                                    0
                                    evaluationDate
                                    2026-10-09T03:14:30.9035686Z
                                    hasBooleanResult
                                    false
                                    hasNumericResult
                                    true
                                    hasTaskVersionId
                                    false
                                    hasEvaluationDate
                                    true
                                    numericResultNullable
                                    value
                                    1
                                    standardDeviation
                                    0
                                    confidenceInterval
                                    0
                                    hasStandardDeviation
                                    false
                                    hasConfidenceInterval
                                    false
                                    hasUnevenConfidenceInterval
                                    false
                                    hasNumericResultPublic
                                    false
                                    customAdditionalResults
                                      hasNumericResultPrivate
                                      false
                                      task_id
                                      984105
                                      sort_order
                                      DESCENDING
                                      source_name
                                      gpqa-diamond-zero-shot/task-056
                                      display_type
                                      percentages
                                      task_version
                                      1
                                      task_display_type
                                      RAW_VALUES
                                      normalization_status
                                      normalized
                                    published_at
                                    2026-10-12T17:49:58.132967500Z
                                    candidate_class
                                    modelVersion
                                    source_revision
                                    b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                    publisher_anchor
                                    openai/gpt-oss-120b
                                    metric_population
                                    32
                                    benchmark_evaluation
                                    true
                                    task_metadata_source
                                    benchmarkVersion
                                    candidate_metadata_source
                                    benchmarkVersionMappings
                                    evaluated at
                                    2026-10-09T03:14:30.903Z
                                    source model id
                                    gpt-oss-120b
                                    Original result ↗

                                    Kaggle Benchmarks

                                    100%

                                    source id
                                    kaggleBenchmarks
                                    leaderboard name
                                    GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-050
                                    dimension
                                    reasoning
                                    metric
                                    GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-050
                                    rank
                                    1
                                    aggregation scope
                                    kaggle
                                    true
                                    status
                                    published
                                    license
                                    Apache-2.0
                                    direction
                                    higherIsBetter
                                    conditions
                                    task
                                    id
                                    984099
                                    name
                                    gpqa-diamond-zero-shot/task-050
                                    version
                                    1
                                    sort_order
                                    DESCENDING
                                    display_type
                                    percentages
                                    benchmark
                                    id
                                    7
                                    name
                                    GPQA Diamond Zero‑Shot
                                    type
                                    INDIVIDUAL
                                    owner
                                    open-benchmarks
                                    version
                                    2
                                    categories
                                    • general knowledge and reasoning
                                    • science
                                    version_id
                                    8176
                                    maintainer_tier
                                    Kaggle-maintained
                                    maintenance_level
                                    KAGGLE_MAINTAINED
                                    candidate
                                    candidate_class
                                    modelVersion
                                    record_kind
                                    aggregate
                                    attribution
                                    Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                                    license_url
                                    https://www.apache.org/licenses/LICENSE-2.0
                                    metric_kind
                                    GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-050
                                    rank_method
                                    competition rank among reported evaluations in identical conditions, including unlinked observations
                                    source_file
                                    8176/leaderboard.json
                                    source_page
                                    https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                                    measurements
                                    • name
                                      gpqa-diamond-zero-shot/task-050
                                      unit
                                      percent
                                      scale
                                      1
                                      metric
                                      GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-050
                                      result
                                      resultCase
                                      numericResult
                                      booleanResult
                                      false
                                      numericResult
                                      value
                                      1
                                      standardDeviation
                                      0
                                      confidenceInterval
                                      0
                                      hasStandardDeviation
                                      false
                                      hasConfidenceInterval
                                      false
                                      hasUnevenConfidenceInterval
                                      false
                                      taskVersionId
                                      0
                                      evaluationDate
                                      2026-10-08T23:59:38.9705675Z
                                      hasBooleanResult
                                      false
                                      hasNumericResult
                                      true
                                      hasTaskVersionId
                                      false
                                      hasEvaluationDate
                                      true
                                      numericResultNullable
                                      value
                                      1
                                      standardDeviation
                                      0
                                      confidenceInterval
                                      0
                                      hasStandardDeviation
                                      false
                                      hasConfidenceInterval
                                      false
                                      hasUnevenConfidenceInterval
                                      false
                                      hasNumericResultPublic
                                      false
                                      customAdditionalResults
                                        hasNumericResultPrivate
                                        false
                                        task_id
                                        984099
                                        sort_order
                                        DESCENDING
                                        source_name
                                        gpqa-diamond-zero-shot/task-050
                                        display_type
                                        percentages
                                        task_version
                                        1
                                        task_display_type
                                        RAW_VALUES
                                        normalization_status
                                        normalized
                                      published_at
                                      2026-10-12T17:49:58.132967500Z
                                      candidate_class
                                      modelVersion
                                      source_revision
                                      b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                      publisher_anchor
                                      openai/gpt-oss-120b
                                      metric_population
                                      32
                                      benchmark_evaluation
                                      true
                                      task_metadata_source
                                      benchmarkVersion
                                      candidate_metadata_source
                                      benchmarkVersionMappings
                                      evaluated at
                                      2026-10-08T23:59:38.970Z
                                      source model id
                                      gpt-oss-120b
                                      Original result ↗

                                      Kaggle Benchmarks

                                      100%

                                      source id
                                      kaggleBenchmarks
                                      leaderboard name
                                      GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-043
                                      dimension
                                      reasoning
                                      metric
                                      GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-043
                                      rank
                                      1
                                      aggregation scope
                                      kaggle
                                      true
                                      status
                                      published
                                      license
                                      Apache-2.0
                                      direction
                                      higherIsBetter
                                      conditions
                                      task
                                      id
                                      984091
                                      name
                                      gpqa-diamond-zero-shot/task-043
                                      version
                                      1
                                      sort_order
                                      DESCENDING
                                      display_type
                                      percentages
                                      benchmark
                                      id
                                      7
                                      name
                                      GPQA Diamond Zero‑Shot
                                      type
                                      INDIVIDUAL
                                      owner
                                      open-benchmarks
                                      version
                                      2
                                      categories
                                      • general knowledge and reasoning
                                      • science
                                      version_id
                                      8176
                                      maintainer_tier
                                      Kaggle-maintained
                                      maintenance_level
                                      KAGGLE_MAINTAINED
                                      candidate
                                      candidate_class
                                      modelVersion
                                      record_kind
                                      aggregate
                                      attribution
                                      Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                                      license_url
                                      https://www.apache.org/licenses/LICENSE-2.0
                                      metric_kind
                                      GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-043
                                      rank_method
                                      competition rank among reported evaluations in identical conditions, including unlinked observations
                                      source_file
                                      8176/leaderboard.json
                                      source_page
                                      https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                                      measurements
                                      • name
                                        gpqa-diamond-zero-shot/task-043
                                        unit
                                        percent
                                        scale
                                        1
                                        metric
                                        GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-043
                                        result
                                        resultCase
                                        numericResult
                                        booleanResult
                                        false
                                        numericResult
                                        value
                                        1
                                        standardDeviation
                                        0
                                        confidenceInterval
                                        0
                                        hasStandardDeviation
                                        false
                                        hasConfidenceInterval
                                        false
                                        hasUnevenConfidenceInterval
                                        false
                                        taskVersionId
                                        0
                                        evaluationDate
                                        2026-10-08T23:55:35.592425Z
                                        hasBooleanResult
                                        false
                                        hasNumericResult
                                        true
                                        hasTaskVersionId
                                        false
                                        hasEvaluationDate
                                        true
                                        numericResultNullable
                                        value
                                        1
                                        standardDeviation
                                        0
                                        confidenceInterval
                                        0
                                        hasStandardDeviation
                                        false
                                        hasConfidenceInterval
                                        false
                                        hasUnevenConfidenceInterval
                                        false
                                        hasNumericResultPublic
                                        false
                                        customAdditionalResults
                                          hasNumericResultPrivate
                                          false
                                          task_id
                                          984091
                                          sort_order
                                          DESCENDING
                                          source_name
                                          gpqa-diamond-zero-shot/task-043
                                          display_type
                                          percentages
                                          task_version
                                          1
                                          task_display_type
                                          RAW_VALUES
                                          normalization_status
                                          normalized
                                        published_at
                                        2026-10-12T17:49:58.132967500Z
                                        candidate_class
                                        modelVersion
                                        source_revision
                                        b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                        publisher_anchor
                                        openai/gpt-oss-120b
                                        metric_population
                                        32
                                        benchmark_evaluation
                                        true
                                        task_metadata_source
                                        benchmarkVersion
                                        candidate_metadata_source
                                        benchmarkVersionMappings
                                        evaluated at
                                        2026-10-08T23:55:35.592Z
                                        source model id
                                        gpt-oss-120b
                                        Original result ↗

                                        Kaggle Benchmarks

                                        100%

                                        source id
                                        kaggleBenchmarks
                                        leaderboard name
                                        GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-188
                                        dimension
                                        reasoning
                                        metric
                                        GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-188
                                        rank
                                        1
                                        aggregation scope
                                        kaggle
                                        true
                                        status
                                        published
                                        license
                                        Apache-2.0
                                        direction
                                        higherIsBetter
                                        conditions
                                        task
                                        id
                                        984238
                                        name
                                        gpqa-diamond-zero-shot/task-188
                                        version
                                        1
                                        sort_order
                                        DESCENDING
                                        display_type
                                        percentages
                                        benchmark
                                        id
                                        7
                                        name
                                        GPQA Diamond Zero‑Shot
                                        type
                                        INDIVIDUAL
                                        owner
                                        open-benchmarks
                                        version
                                        2
                                        categories
                                        • general knowledge and reasoning
                                        • science
                                        version_id
                                        8176
                                        maintainer_tier
                                        Kaggle-maintained
                                        maintenance_level
                                        KAGGLE_MAINTAINED
                                        candidate
                                        candidate_class
                                        modelVersion
                                        record_kind
                                        aggregate
                                        attribution
                                        Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
                                        license_url
                                        https://www.apache.org/licenses/LICENSE-2.0
                                        metric_kind
                                        GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-188
                                        rank_method
                                        competition rank among reported evaluations in identical conditions, including unlinked observations
                                        source_file
                                        8176/leaderboard.json
                                        source_page
                                        https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
                                        measurements
                                        • name
                                          gpqa-diamond-zero-shot/task-188
                                          unit
                                          percent
                                          scale
                                          1
                                          metric
                                          GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-188
                                          result
                                          resultCase
                                          numericResult
                                          booleanResult
                                          false
                                          numericResult
                                          value
                                          1
                                          standardDeviation
                                          0
                                          confidenceInterval
                                          0
                                          hasStandardDeviation
                                          false
                                          hasConfidenceInterval
                                          false
                                          hasUnevenConfidenceInterval
                                          false
                                          taskVersionId
                                          0
                                          evaluationDate
                                          2026-10-09T02:44:15.8622518Z
                                          hasBooleanResult
                                          false
                                          hasNumericResult
                                          true
                                          hasTaskVersionId
                                          false
                                          hasEvaluationDate
                                          true
                                          numericResultNullable
                                          value
                                          1
                                          standardDeviation
                                          0
                                          confidenceInterval
                                          0
                                          hasStandardDeviation
                                          false
                                          hasConfidenceInterval
                                          false
                                          hasUnevenConfidenceInterval
                                          false
                                          hasNumericResultPublic
                                          false
                                          customAdditionalResults
                                            hasNumericResultPrivate
                                            false
                                            task_id
                                            984238
                                            sort_order
                                            DESCENDING
                                            source_name
                                            gpqa-diamond-zero-shot/task-188
                                            display_type
                                            percentages
                                            task_version
                                            1
                                            task_display_type
                                            RAW_VALUES
                                            normalization_status
                                            normalized
                                          published_at
                                          2026-10-12T17:49:58.132967500Z
                                          candidate_class
                                          modelVersion
                                          source_revision
                                          b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                          publisher_anchor
                                          openai/gpt-oss-120b
                                          metric_population
                                          32
                                          benchmark_evaluation
                                          true
                                          task_metadata_source
                                          benchmarkVersion
                                          candidate_metadata_source
                                          benchmarkVersionMappings
                                          evaluated at
                                          2026-10-09T02:44:15.862Z
                                          source model id
                                          gpt-oss-120b
                                          Original result ↗

                                          Published prices

                                          1–20 / 43

                                          gpt-oss-120b ↗

                                          $0.01

                                          Inference provider
                                          cheaperInference
                                          Platform
                                          Cheaper Inference
                                          Unit
                                          cache_read_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          zdr
                                          false
                                          protocol
                                          chat_completions
                                          service_tier
                                          standard
                                          Billing label
                                          Cached input tokens (per 1M)

                                          gpt-oss-120b ↗

                                          $0.05

                                          Inference provider
                                          cheaperInference
                                          Platform
                                          Cheaper Inference
                                          Unit
                                          input_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          zdr
                                          false
                                          protocol
                                          chat_completions
                                          service_tier
                                          standard
                                          Billing label
                                          Input tokens (per 1M)

                                          gpt-oss-120b ↗

                                          $0.26

                                          Inference provider
                                          cheaperInference
                                          Platform
                                          Cheaper Inference
                                          Unit
                                          output_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          zdr
                                          false
                                          protocol
                                          chat_completions
                                          service_tier
                                          standard
                                          Billing label
                                          Output tokens (per 1M)

                                          @cf/openai/gpt-oss-120b ↗

                                          $0.35

                                          Inference provider
                                          cloudflareWorkersAI
                                          Platform
                                          Cloudflare Workers AI
                                          Unit
                                          input_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          Billing label
                                          per M input tokens

                                          @cf/openai/gpt-oss-120b ↗

                                          $0.75

                                          Inference provider
                                          cloudflareWorkersAI
                                          Platform
                                          Cloudflare Workers AI
                                          Unit
                                          output_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          Billing label
                                          per M output tokens

                                          openai/gpt-oss-120b ↗

                                          $0.04

                                          Inference provider
                                          deepInfra
                                          Platform
                                          DeepInfra
                                          Unit
                                          input_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions

                                          openai/gpt-oss-120b ↗

                                          $0.17

                                          Inference provider
                                          deepInfra
                                          Platform
                                          DeepInfra
                                          Unit
                                          output_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions

                                          openai/gpt-oss-120b ↗

                                          $0.08

                                          Inference provider
                                          openRouter
                                          Platform
                                          OpenRouter
                                          Unit
                                          cache_read_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions

                                          openai/gpt-oss-120b ↗

                                          $0.15

                                          Inference provider
                                          openRouter
                                          Platform
                                          OpenRouter
                                          Unit
                                          input_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions

                                          openai/gpt-oss-120b ↗

                                          $0.60

                                          Inference provider
                                          openRouter
                                          Platform
                                          OpenRouter
                                          Unit
                                          output_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions

                                          openai/gpt-oss-120b:batch ↗

                                          $0.03

                                          Inference provider
                                          openRouter
                                          Platform
                                          OpenRouter
                                          Unit
                                          input_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          mode
                                          batch

                                          openai/gpt-oss-120b:batch ↗

                                          $0.14

                                          Inference provider
                                          openRouter
                                          Platform
                                          OpenRouter
                                          Unit
                                          output_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          mode
                                          batch

                                          openai/gpt-oss-120b ↗

                                          $0.08

                                          Inference provider
                                          siliconFlow
                                          Platform
                                          SiliconFlow
                                          Unit
                                          cache_read_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          Billing label
                                          Cached input tokens (per 1M)

                                          openai/gpt-oss-120b ↗

                                          $0.05

                                          Inference provider
                                          siliconFlow
                                          Platform
                                          SiliconFlow
                                          Unit
                                          input_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          Billing label
                                          Input tokens (per 1M)

                                          openai/gpt-oss-120b ↗

                                          $0.45

                                          Inference provider
                                          siliconFlow
                                          Platform
                                          SiliconFlow
                                          Unit
                                          output_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          Billing label
                                          Output tokens (per 1M)

                                          openai/gpt-oss-120b ↗

                                          $0.10

                                          Inference provider
                                          vercelAIGatewayCatalog
                                          Platform
                                          baseten
                                          Unit
                                          cache_read_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          endpoint
                                          baseten | openai/gpt-oss-120b
                                          model_type
                                          language
                                          quantization
                                          fp4
                                          billing_scope
                                          via Vercel AI Gateway
                                          Billing label
                                          Cached input / 1M
                                          Pricing via
                                          Vercel AI Gateway

                                          openai/gpt-oss-120b ↗

                                          $0.10

                                          Inference provider
                                          vercelAIGatewayCatalog
                                          Platform
                                          baseten
                                          Unit
                                          cache_read_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          region
                                          scope
                                          zone
                                          geo_region
                                          us
                                          endpoint
                                          baseten | openai/gpt-oss-120b
                                          model_type
                                          language
                                          quantization
                                          fp4
                                          billing_scope
                                          via Vercel AI Gateway
                                          Billing label
                                          Cached input / 1M
                                          Pricing via
                                          Vercel AI Gateway

                                          openai/gpt-oss-120b ↗

                                          $0.10

                                          Inference provider
                                          vercelAIGatewayCatalog
                                          Platform
                                          baseten
                                          Unit
                                          input_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          endpoint
                                          baseten | openai/gpt-oss-120b
                                          model_type
                                          language
                                          quantization
                                          fp4
                                          billing_scope
                                          via Vercel AI Gateway
                                          Billing label
                                          Input tokens / 1M
                                          Pricing via
                                          Vercel AI Gateway

                                          openai/gpt-oss-120b ↗

                                          $0.10

                                          Inference provider
                                          vercelAIGatewayCatalog
                                          Platform
                                          baseten
                                          Unit
                                          input_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          region
                                          scope
                                          zone
                                          geo_region
                                          us
                                          endpoint
                                          baseten | openai/gpt-oss-120b
                                          model_type
                                          language
                                          quantization
                                          fp4
                                          billing_scope
                                          via Vercel AI Gateway
                                          Billing label
                                          Input tokens / 1M
                                          Pricing via
                                          Vercel AI Gateway

                                          openai/gpt-oss-120b ↗

                                          $0.50

                                          Inference provider
                                          vercelAIGatewayCatalog
                                          Platform
                                          baseten
                                          Unit
                                          output_tokens_per_million
                                          Currency
                                          USD
                                          Billing conditions
                                          endpoint
                                          baseten | openai/gpt-oss-120b
                                          model_type
                                          language
                                          quantization
                                          fp4
                                          billing_scope
                                          via Vercel AI Gateway
                                          Billing label
                                          Output tokens / 1M
                                          Pricing via
                                          Vercel AI Gateway

                                          Deployments & artifacts

                                          1–1 / 1

                                          ollama

                                          source id
                                          ollama
                                          execution mode
                                          cloud
                                          parameter size
                                          116829156672
                                          parameter count
                                          116829156672
                                          parameter count is approximate
                                          false
                                          quantization level
                                          MXFP4
                                          context window
                                          131072
                                          context window is approximate
                                          false
                                          artifact size bytes
                                          65290180781
                                          architecture
                                          gptoss
                                          thinking
                                          values
                                          • low
                                          • medium
                                          • high
                                          default
                                          medium
                                          updated at
                                          2026-11-16T08:10:06.079865+00:00
                                          Confirmed base model
                                          openai/gpt-oss-120b

                                          Provider specifications & access

                                          1–16 / 16

                                          openai/gpt-oss-120b ↗

                                          source model id
                                          azure-huggingface/openai--gpt-oss-120b@1
                                          hosting
                                          foundry-managed-compute
                                          platforms
                                          • Microsoft Foundry
                                          license
                                          apache-2.0
                                          context length
                                          131072
                                          architecture
                                          input_modalities
                                          • text
                                          output_modalities
                                          • text
                                          capabilities

                                            openai/gpt-oss-120b ↗

                                            source model id
                                            azure-huggingface/openai--gpt-oss-120b@2
                                            hosting
                                            foundry-managed-compute
                                            platforms
                                            • Microsoft Foundry
                                            license
                                            apache-2.0
                                            context length
                                            131072
                                            architecture
                                            input_modalities
                                            • text
                                            output_modalities
                                            • text
                                            capabilities

                                              openai/gpt-oss-120b ↗

                                              source model id
                                              azure-huggingface/openai--gpt-oss-120b@3
                                              hosting
                                              foundry-managed-compute
                                              platforms
                                              • Microsoft Foundry
                                              license
                                              apache-2.0
                                              context length
                                              131072
                                              architecture
                                              input_modalities
                                              • text
                                              output_modalities
                                              • text
                                              capabilities

                                                openai/gpt-oss-120b ↗

                                                source model id
                                                azure-huggingface/openai--gpt-oss-120b@4
                                                hosting
                                                foundry-managed-compute
                                                platforms
                                                • Microsoft Foundry
                                                license
                                                apache-2.0
                                                context length
                                                131072
                                                architecture
                                                input_modalities
                                                • text
                                                output_modalities
                                                • text
                                                capabilities

                                                  openai/gpt-oss-120b ↗

                                                  source model id
                                                  azure-huggingface/openai--gpt-oss-120b@5
                                                  hosting
                                                  foundry-managed-compute
                                                  platforms
                                                  • Microsoft Foundry
                                                  license
                                                  apache-2.0
                                                  context length
                                                  131072
                                                  architecture
                                                  input_modalities
                                                  • text
                                                  output_modalities
                                                  • text
                                                  capabilities

                                                    openai/gpt-oss-120b ↗

                                                    source model id
                                                    azure-huggingface/openai--gpt-oss-120b@6
                                                    hosting
                                                    foundry-managed-compute
                                                    platforms
                                                    • Microsoft Foundry
                                                    license
                                                    apache-2.0
                                                    context length
                                                    131072
                                                    architecture
                                                    input_modalities
                                                    • text
                                                    output_modalities
                                                    • text
                                                    capabilities

                                                      openai/gpt-oss-120b ↗

                                                      source model id
                                                      azure-huggingface/openai--gpt-oss-120b@7
                                                      hosting
                                                      foundry-managed-compute
                                                      platforms
                                                      • Microsoft Foundry
                                                      license
                                                      apache-2.0
                                                      context length
                                                      131072
                                                      architecture
                                                      input_modalities
                                                      • text
                                                      output_modalities
                                                      • text
                                                      capabilities

                                                        openai/gpt-oss-120b ↗

                                                        source model id
                                                        azure-huggingface/openai--gpt-oss-120b@8
                                                        hosting
                                                        foundry-managed-compute
                                                        platforms
                                                        • Microsoft Foundry
                                                        license
                                                        apache-2.0
                                                        context length
                                                        131072
                                                        architecture
                                                        input_modalities
                                                        • text
                                                        output_modalities
                                                        • text
                                                        capabilities

                                                          gpt-oss-120b ↗

                                                          source model id
                                                          @cf/openai/gpt-oss-120b
                                                          hosting
                                                          cloudflare-hosted
                                                          platforms
                                                          • Cloudflare Workers AI
                                                          context length
                                                          128000
                                                          architecture
                                                          input_modalities
                                                          • text
                                                          output_modalities
                                                          • text
                                                          capabilities
                                                          • toolCalling

                                                          gpt-oss-120b ↗

                                                          source model id
                                                          gpt-oss-120b
                                                          hosting
                                                          gateway
                                                          platforms
                                                          • Cheaper Inference
                                                          context length
                                                          128000
                                                          max output tokens
                                                          131072
                                                          architecture
                                                          input_modalities
                                                          • text
                                                          output_modalities
                                                          • text
                                                          capabilities
                                                          • structuredOutputs
                                                          • toolCalling

                                                          openai/gpt-oss-120b ↗

                                                          source model id
                                                          HuggingFace/openai-gpt-oss-120b@1
                                                          hosting
                                                          foundry-managed-compute
                                                          platforms
                                                          • Microsoft Foundry
                                                          license
                                                          apache-2.0
                                                          architecture
                                                          input_modalities
                                                          • text
                                                          output_modalities
                                                          • text
                                                          capabilities

                                                            openai/gpt-oss-120b ↗

                                                            source model id
                                                            HuggingFace/openai-gpt-oss-120b@2
                                                            hosting
                                                            foundry-managed-compute
                                                            platforms
                                                            • Microsoft Foundry
                                                            license
                                                            apache-2.0
                                                            architecture
                                                            input_modalities
                                                            • text
                                                            output_modalities
                                                            • text
                                                            capabilities

                                                              gpt-oss-120b ↗

                                                              source model id
                                                              openai/gpt-oss-120b
                                                              hosting
                                                              siliconflow-hosted
                                                              platforms
                                                              • SiliconFlow
                                                              max output tokens
                                                              8192
                                                              architecture
                                                              input_modalities
                                                              • text
                                                              output_modalities
                                                              • text
                                                              capabilities
                                                              • promptCaching
                                                              • structuredOutputs

                                                              GPT OSS 120B ↗

                                                              source model id
                                                              openai/gpt-oss-120b
                                                              hosting
                                                              vercel-gateway
                                                              platforms
                                                              • Vercel AI Gateway
                                                              context length
                                                              131072
                                                              max output tokens
                                                              131072
                                                              architecture
                                                              input_modalities
                                                              • text
                                                              output_modalities
                                                              • text
                                                              capabilities
                                                              • promptCaching
                                                              • reasoning
                                                              • structuredOutputs
                                                              • toolCalling
                                                              regions
                                                              • us

                                                              openai/gpt-oss-120b ↗

                                                              source model id
                                                              publishers/hf-openai/models/gpt-oss-120b@001
                                                              hosting
                                                              vertex-self-deployed
                                                              platforms
                                                              • Google Cloud Vertex AI
                                                              architecture
                                                              input_modalities
                                                              • text
                                                              output_modalities
                                                              • text
                                                              capabilities

                                                                gpt-oss-120b ↗

                                                                source model id
                                                                publishers/openai/models/gpt-oss@gpt-oss-120b
                                                                hosting
                                                                vertex-self-deployed
                                                                platforms
                                                                • Google Cloud Vertex AI
                                                                architecture
                                                                input_modalities
                                                                • text
                                                                output_modalities
                                                                • text
                                                                capabilities

                                                                  Safety assessments

                                                                  1–1 / 1

                                                                  Foundation Model Transparency Index 2025 ↗

                                                                  35 / 100

                                                                  source id
                                                                  stanfordFMTI
                                                                  canonical model id
                                                                  openai/gpt-oss-120b
                                                                  taxonomy
                                                                  transparency
                                                                  hazard category
                                                                  transparency
                                                                  hazard name
                                                                  Organization transparency
                                                                  policy area
                                                                  OpenAI
                                                                  assessment type
                                                                  organization-level disclosure
                                                                  metric
                                                                  disclosure_score
                                                                  result label
                                                                  35 / 100
                                                                  sample size
                                                                  100
                                                                  updated at
                                                                  2026-11-09T18:08:05.227Z

                                                                  Source specification observations

                                                                  1–19 / 19

                                                                  azureFoundry ↗

                                                                  field
                                                                  context_length
                                                                  value
                                                                  131072
                                                                  normalized value
                                                                  131072
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  azureFoundry
                                                                  confidence
                                                                  1

                                                                  azureFoundry ↗

                                                                  field
                                                                  context_length
                                                                  value
                                                                  131072
                                                                  normalized value
                                                                  131072
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  azureFoundry
                                                                  confidence
                                                                  1

                                                                  azureFoundry ↗

                                                                  field
                                                                  context_length
                                                                  value
                                                                  131072
                                                                  normalized value
                                                                  131072
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  azureFoundry
                                                                  confidence
                                                                  1

                                                                  azureFoundry ↗

                                                                  field
                                                                  context_length
                                                                  value
                                                                  131072
                                                                  normalized value
                                                                  131072
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  azureFoundry
                                                                  confidence
                                                                  1

                                                                  azureFoundry ↗

                                                                  field
                                                                  context_length
                                                                  value
                                                                  131072
                                                                  normalized value
                                                                  131072
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  azureFoundry
                                                                  confidence
                                                                  1

                                                                  azureFoundry ↗

                                                                  field
                                                                  context_length
                                                                  value
                                                                  131072
                                                                  normalized value
                                                                  131072
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  azureFoundry
                                                                  confidence
                                                                  1

                                                                  azureFoundry ↗

                                                                  field
                                                                  context_length
                                                                  value
                                                                  131072
                                                                  normalized value
                                                                  131072
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  azureFoundry
                                                                  confidence
                                                                  1

                                                                  azureFoundry ↗

                                                                  field
                                                                  context_length
                                                                  value
                                                                  131072
                                                                  normalized value
                                                                  131072
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  azureFoundry
                                                                  confidence
                                                                  1

                                                                  openRouter ↗

                                                                  field
                                                                  context_length
                                                                  value
                                                                  131072
                                                                  normalized value
                                                                  131072
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  openRouter
                                                                  confidence
                                                                  1

                                                                  openRouter ↗

                                                                  field
                                                                  context_length
                                                                  value
                                                                  131072
                                                                  normalized value
                                                                  131072
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  openRouter
                                                                  confidence
                                                                  1

                                                                  siliconFlow ↗

                                                                  field
                                                                  context_length
                                                                  value
                                                                  131K
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  siliconFlow
                                                                  confidence
                                                                  1

                                                                  vercelAIGatewayCatalog ↗

                                                                  field
                                                                  context_length
                                                                  value
                                                                  131072
                                                                  normalized value
                                                                  131072
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  vercelAIGatewayCatalog
                                                                  confidence
                                                                  1

                                                                  openRouter ↗

                                                                  field
                                                                  knowledge_cutoff
                                                                  reported field
                                                                  knowledge_cutoff
                                                                  value
                                                                  2024-06-30
                                                                  normalized value
                                                                  2024-06-30
                                                                  precision
                                                                  day
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  openRouter
                                                                  confidence
                                                                  1

                                                                  openRouter ↗

                                                                  field
                                                                  knowledge_cutoff
                                                                  reported field
                                                                  knowledge_cutoff
                                                                  value
                                                                  2024-06-30
                                                                  normalized value
                                                                  2024-06-30
                                                                  precision
                                                                  day
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  openRouter
                                                                  confidence
                                                                  1

                                                                  vercelAIGatewayCatalog ↗

                                                                  field
                                                                  knowledge_cutoff
                                                                  reported field
                                                                  knowledge_cutoff
                                                                  value
                                                                  2024-06-01
                                                                  normalized value
                                                                  2024-06-01
                                                                  precision
                                                                  day
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  vercelAIGatewayCatalog
                                                                  confidence
                                                                  1

                                                                  openRouter ↗

                                                                  field
                                                                  max_output_tokens
                                                                  value
                                                                  65536
                                                                  normalized value
                                                                  65536
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  openRouter
                                                                  confidence
                                                                  1

                                                                  openRouter ↗

                                                                  field
                                                                  max_output_tokens
                                                                  value
                                                                  117964
                                                                  normalized value
                                                                  117964
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  openRouter
                                                                  confidence
                                                                  1

                                                                  siliconFlow ↗

                                                                  field
                                                                  max_output_tokens
                                                                  value
                                                                  8K
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  siliconFlow
                                                                  confidence
                                                                  1

                                                                  vercelAIGatewayCatalog ↗

                                                                  field
                                                                  max_output_tokens
                                                                  value
                                                                  131072
                                                                  normalized value
                                                                  131072
                                                                  scope
                                                                  source-model
                                                                  source id
                                                                  vercelAIGatewayCatalog
                                                                  confidence
                                                                  1

                                                                  Original sources

                                                                  41–42 / 42

                                                                  Vercel AI Gateway · Catalog ↗

                                                                  crfm.stanford.edu · Catalog ↗

                                                                  Source links

                                                                  1–19 / 19

                                                                  Hugging Face model card

                                                                  1–1 / 1

                                                                  openai/gpt-oss-120b ↗

                                                                  downloads
                                                                  2430934
                                                                  likes
                                                                  5507
                                                                  pipeline tag
                                                                  text-generation
                                                                  library name
                                                                  transformers
                                                                  License
                                                                  apache-2.0

                                                                  Explore more models

                                                                  Models

                                                                  Loading
                                                                  EVIDENCE / COMPARISON

                                                                  Benchmarks

                                                                  Explore every benchmark

                                                                  Loading

                                                                  These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

                                                                  Install TensorTrace