OpenAI: GPT-4.1

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and …

openai/gpt-4.1-2025-04-14

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.

Specifications & capabilities

Input
image, text, file
Output
text
Context window · tokens
1047576
Published model ID
gpt-4.1-2025-04-14
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗

Evaluations

21–40 / 257

Kaggle Benchmarks

40.8%

source id
kaggleBenchmarks
leaderboard name
MultiLoKo Italian · EM Italian
dimension
reasoning
metric
MultiLoKo Italian · EM Italian
rank
10
aggregation scope
kaggle
true
status
published
license
Apache-2.0
direction
higherIsBetter
conditions
task
id
41
name
EM Italian
version
1
sort_order
DESCENDING
display_type
percentages
benchmark
id
64
name
MultiLoKo Italian
type
INDIVIDUAL
owner
metaresearch
version
1
categories
  • multilingual and cross-lingual capabilities
  • general knowledge and reasoning
version_id
50
maintainer_tier
Kaggle-maintained
maintenance_level
KAGGLE_MAINTAINED
candidate
candidate_class
modelVersion
record_kind
aggregate
attribution
Kaggle · metaresearch · MultiLoKo Italian
license_url
https://www.apache.org/licenses/LICENSE-2.0
metric_kind
MultiLoKo Italian · EM Italian
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
50/leaderboard.json
source_page
https://www.kaggle.com/benchmarks/metaresearch/multiloko-italian/versions/1
measurements
  • name
    EM Italian
    unit
    percent
    scale
    1
    metric
    MultiLoKo Italian · EM Italian
    result
    resultCase
    numericResult
    booleanResult
    false
    numericResult
    value
    0.408
    standardDeviation
    0
    confidenceInterval
    0.0609212802792317
    hasStandardDeviation
    false
    hasConfidenceInterval
    true
    confidenceIntervalNullable
    0.0609212802792317
    hasUnevenConfidenceInterval
    false
    taskVersionId
    0
    evaluationDate
    2025-06-16T00:00:00Z
    hasBooleanResult
    false
    hasNumericResult
    true
    hasTaskVersionId
    false
    hasEvaluationDate
    true
    numericResultNullable
    value
    0.408
    standardDeviation
    0
    confidenceInterval
    0.0609212802792317
    hasStandardDeviation
    false
    hasConfidenceInterval
    true
    confidenceIntervalNullable
    0.0609212802792317
    hasUnevenConfidenceInterval
    false
    hasNumericResultPublic
    false
    customAdditionalResults
      hasNumericResultPrivate
      false
      task_id
      41
      sort_order
      DESCENDING
      source_name
      EM Italian
      display_type
      percentages
      task_version
      1
      task_display_type
      PERCENTAGES
      normalization_status
      normalized
    published_at
    2025-07-15T11:49:31.790Z
    candidate_class
    modelVersion
    source_revision
    b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
    publisher_anchor
    openai/gpt-4.1-2025-04-14
    metric_population
    51
    benchmark_evaluation
    true
    task_metadata_source
    benchmarkVersion
    candidate_metadata_source
    benchmarkVersionMappings
    evaluated at
    2025-06-16T00:00:00.000Z
    source model id
    GPT-4.1
    confidence lower
    0.34707871972076826
    confidence upper
    0.4689212802792317
    Original result ↗

    Kaggle Benchmarks

    38.4%

    source id
    kaggleBenchmarks
    leaderboard name
    MultiLoKo Hindi · EM Hindi
    dimension
    reasoning
    metric
    MultiLoKo Hindi · EM Hindi
    rank
    10
    aggregation scope
    kaggle
    true
    status
    published
    license
    Apache-2.0
    direction
    higherIsBetter
    conditions
    task
    id
    39
    name
    EM Hindi
    version
    1
    sort_order
    DESCENDING
    display_type
    percentages
    benchmark
    id
    62
    name
    MultiLoKo Hindi
    type
    INDIVIDUAL
    owner
    metaresearch
    version
    1
    categories
    • multilingual and cross-lingual capabilities
    • general knowledge and reasoning
    version_id
    48
    maintainer_tier
    Kaggle-maintained
    maintenance_level
    KAGGLE_MAINTAINED
    candidate
    candidate_class
    modelVersion
    record_kind
    aggregate
    attribution
    Kaggle · metaresearch · MultiLoKo Hindi
    license_url
    https://www.apache.org/licenses/LICENSE-2.0
    metric_kind
    MultiLoKo Hindi · EM Hindi
    rank_method
    competition rank among reported evaluations in identical conditions, including unlinked observations
    source_file
    48/leaderboard.json
    source_page
    https://www.kaggle.com/benchmarks/metaresearch/multiloko-hindi/versions/1
    measurements
    • name
      EM Hindi
      unit
      percent
      scale
      1
      metric
      MultiLoKo Hindi · EM Hindi
      result
      resultCase
      numericResult
      booleanResult
      false
      numericResult
      value
      0.384
      standardDeviation
      0
      confidenceInterval
      0.0602884411900746
      hasStandardDeviation
      false
      hasConfidenceInterval
      true
      confidenceIntervalNullable
      0.0602884411900746
      hasUnevenConfidenceInterval
      false
      taskVersionId
      0
      evaluationDate
      2025-06-16T00:00:00Z
      hasBooleanResult
      false
      hasNumericResult
      true
      hasTaskVersionId
      false
      hasEvaluationDate
      true
      numericResultNullable
      value
      0.384
      standardDeviation
      0
      confidenceInterval
      0.0602884411900746
      hasStandardDeviation
      false
      hasConfidenceInterval
      true
      confidenceIntervalNullable
      0.0602884411900746
      hasUnevenConfidenceInterval
      false
      hasNumericResultPublic
      false
      customAdditionalResults
        hasNumericResultPrivate
        false
        task_id
        39
        sort_order
        DESCENDING
        source_name
        EM Hindi
        display_type
        percentages
        task_version
        1
        task_display_type
        PERCENTAGES
        normalization_status
        normalized
      published_at
      2025-07-15T11:49:31.790Z
      candidate_class
      modelVersion
      source_revision
      b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
      publisher_anchor
      openai/gpt-4.1-2025-04-14
      metric_population
      51
      benchmark_evaluation
      true
      task_metadata_source
      benchmarkVersion
      candidate_metadata_source
      benchmarkVersionMappings
      evaluated at
      2025-06-16T00:00:00.000Z
      source model id
      GPT-4.1
      confidence lower
      0.3237115588099254
      confidence upper
      0.4442884411900746
      Original result ↗

      Kaggle Benchmarks

      34.8%

      source id
      kaggleBenchmarks
      leaderboard name
      MultiLoKo Romanian · EM Romanian
      dimension
      reasoning
      metric
      MultiLoKo Romanian · EM Romanian
      rank
      10
      aggregation scope
      kaggle
      true
      status
      published
      license
      Apache-2.0
      direction
      higherIsBetter
      conditions
      task
      id
      49
      name
      EM Romanian
      version
      1
      sort_order
      DESCENDING
      display_type
      percentages
      benchmark
      id
      72
      name
      MultiLoKo Romanian
      type
      INDIVIDUAL
      owner
      metaresearch
      version
      1
      categories
      • multilingual and cross-lingual capabilities
      • general knowledge and reasoning
      version_id
      58
      maintainer_tier
      Kaggle-maintained
      maintenance_level
      KAGGLE_MAINTAINED
      candidate
      candidate_class
      modelVersion
      record_kind
      aggregate
      attribution
      Kaggle · metaresearch · MultiLoKo Romanian
      license_url
      https://www.apache.org/licenses/LICENSE-2.0
      metric_kind
      MultiLoKo Romanian · EM Romanian
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      58/leaderboard.json
      source_page
      https://www.kaggle.com/benchmarks/metaresearch/multiloko-romanian/versions/1
      measurements
      • name
        EM Romanian
        unit
        percent
        scale
        1
        metric
        MultiLoKo Romanian · EM Romanian
        result
        resultCase
        numericResult
        booleanResult
        false
        numericResult
        value
        0.348
        standardDeviation
        0
        confidenceInterval
        0.0590461392668551
        hasStandardDeviation
        false
        hasConfidenceInterval
        true
        confidenceIntervalNullable
        0.0590461392668551
        hasUnevenConfidenceInterval
        false
        taskVersionId
        0
        evaluationDate
        2025-06-16T00:00:00Z
        hasBooleanResult
        false
        hasNumericResult
        true
        hasTaskVersionId
        false
        hasEvaluationDate
        true
        numericResultNullable
        value
        0.348
        standardDeviation
        0
        confidenceInterval
        0.0590461392668551
        hasStandardDeviation
        false
        hasConfidenceInterval
        true
        confidenceIntervalNullable
        0.0590461392668551
        hasUnevenConfidenceInterval
        false
        hasNumericResultPublic
        false
        customAdditionalResults
          hasNumericResultPrivate
          false
          task_id
          49
          sort_order
          DESCENDING
          source_name
          EM Romanian
          display_type
          percentages
          task_version
          1
          task_display_type
          PERCENTAGES
          normalization_status
          normalized
        published_at
        2025-07-15T11:49:31.790Z
        candidate_class
        modelVersion
        source_revision
        b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
        publisher_anchor
        openai/gpt-4.1-2025-04-14
        metric_population
        51
        benchmark_evaluation
        true
        task_metadata_source
        benchmarkVersion
        candidate_metadata_source
        benchmarkVersionMappings
        evaluated at
        2025-06-16T00:00:00.000Z
        source model id
        GPT-4.1
        confidence lower
        0.2889538607331449
        confidence upper
        0.40704613926685507
        Original result ↗

        Kaggle Benchmarks

        22%

        source id
        kaggleBenchmarks
        leaderboard name
        MultiLoKo Malay · EM Malay
        dimension
        reasoning
        metric
        MultiLoKo Malay · EM Malay
        rank
        10
        aggregation scope
        kaggle
        true
        status
        published
        license
        Apache-2.0
        direction
        higherIsBetter
        conditions
        task
        id
        45
        name
        EM Malay
        version
        1
        sort_order
        DESCENDING
        display_type
        percentages
        benchmark
        id
        68
        name
        MultiLoKo Malay
        type
        INDIVIDUAL
        owner
        metaresearch
        version
        1
        categories
        • multilingual and cross-lingual capabilities
        • general knowledge and reasoning
        version_id
        54
        maintainer_tier
        Kaggle-maintained
        maintenance_level
        KAGGLE_MAINTAINED
        candidate
        candidate_class
        modelVersion
        record_kind
        aggregate
        attribution
        Kaggle · metaresearch · MultiLoKo Malay
        license_url
        https://www.apache.org/licenses/LICENSE-2.0
        metric_kind
        MultiLoKo Malay · EM Malay
        rank_method
        competition rank among reported evaluations in identical conditions, including unlinked observations
        source_file
        54/leaderboard.json
        source_page
        https://www.kaggle.com/benchmarks/metaresearch/multiloko-malay/versions/1
        measurements
        • name
          EM Malay
          unit
          percent
          scale
          1
          metric
          MultiLoKo Malay · EM Malay
          result
          resultCase
          numericResult
          booleanResult
          false
          numericResult
          value
          0.22
          standardDeviation
          0
          confidenceInterval
          0.0513495602174395
          hasStandardDeviation
          false
          hasConfidenceInterval
          true
          confidenceIntervalNullable
          0.0513495602174395
          hasUnevenConfidenceInterval
          false
          taskVersionId
          0
          evaluationDate
          2025-06-16T00:00:00Z
          hasBooleanResult
          false
          hasNumericResult
          true
          hasTaskVersionId
          false
          hasEvaluationDate
          true
          numericResultNullable
          value
          0.22
          standardDeviation
          0
          confidenceInterval
          0.0513495602174395
          hasStandardDeviation
          false
          hasConfidenceInterval
          true
          confidenceIntervalNullable
          0.0513495602174395
          hasUnevenConfidenceInterval
          false
          hasNumericResultPublic
          false
          customAdditionalResults
            hasNumericResultPrivate
            false
            task_id
            45
            sort_order
            DESCENDING
            source_name
            EM Malay
            display_type
            percentages
            task_version
            1
            task_display_type
            PERCENTAGES
            normalization_status
            normalized
          published_at
          2025-07-15T11:49:31.790Z
          candidate_class
          modelVersion
          source_revision
          b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
          publisher_anchor
          openai/gpt-4.1-2025-04-14
          metric_population
          51
          benchmark_evaluation
          true
          task_metadata_source
          benchmarkVersion
          candidate_metadata_source
          benchmarkVersionMappings
          evaluated at
          2025-06-16T00:00:00.000Z
          source model id
          GPT-4.1
          confidence lower
          0.1686504397825605
          confidence upper
          0.2713495602174395
          Original result ↗

          LMArena

          1,233.696

          source id
          lmarena
          leaderboard name
          LMArena Vision Style Control Creative Writing
          dimension
          multimodal
          metric
          Arena rating
          rank
          11
          sample size
          1432
          evaluated at
          2026-01-09T00:00:00.000Z
          source model id
          gpt-4.1-2025-04-14
          confidence lower
          1217.2341934958322
          confidence upper
          1250.158741575339
          Original result ↗

          Kaggle Benchmarks

          42.8%

          source id
          kaggleBenchmarks
          leaderboard name
          MultiLoKo Portuguese · EM Portuguese
          dimension
          reasoning
          metric
          MultiLoKo Portuguese · EM Portuguese
          rank
          11
          aggregation scope
          kaggle
          true
          status
          published
          license
          Apache-2.0
          direction
          higherIsBetter
          conditions
          task
          id
          48
          name
          EM Portuguese
          version
          1
          sort_order
          DESCENDING
          display_type
          percentages
          benchmark
          id
          71
          name
          MultiLoKo Portuguese
          type
          INDIVIDUAL
          owner
          metaresearch
          version
          1
          categories
          • multilingual and cross-lingual capabilities
          • general knowledge and reasoning
          version_id
          57
          maintainer_tier
          Kaggle-maintained
          maintenance_level
          KAGGLE_MAINTAINED
          candidate
          candidate_class
          modelVersion
          record_kind
          aggregate
          attribution
          Kaggle · metaresearch · MultiLoKo Portuguese
          license_url
          https://www.apache.org/licenses/LICENSE-2.0
          metric_kind
          MultiLoKo Portuguese · EM Portuguese
          rank_method
          competition rank among reported evaluations in identical conditions, including unlinked observations
          source_file
          57/leaderboard.json
          source_page
          https://www.kaggle.com/benchmarks/metaresearch/multiloko-portuguese/versions/1
          measurements
          • name
            EM Portuguese
            unit
            percent
            scale
            1
            metric
            MultiLoKo Portuguese · EM Portuguese
            result
            resultCase
            numericResult
            booleanResult
            false
            numericResult
            value
            0.428
            standardDeviation
            0
            confidenceInterval
            0.0613335334917874
            hasStandardDeviation
            false
            hasConfidenceInterval
            true
            confidenceIntervalNullable
            0.0613335334917874
            hasUnevenConfidenceInterval
            false
            taskVersionId
            0
            evaluationDate
            2025-06-16T00:00:00Z
            hasBooleanResult
            false
            hasNumericResult
            true
            hasTaskVersionId
            false
            hasEvaluationDate
            true
            numericResultNullable
            value
            0.428
            standardDeviation
            0
            confidenceInterval
            0.0613335334917874
            hasStandardDeviation
            false
            hasConfidenceInterval
            true
            confidenceIntervalNullable
            0.0613335334917874
            hasUnevenConfidenceInterval
            false
            hasNumericResultPublic
            false
            customAdditionalResults
              hasNumericResultPrivate
              false
              task_id
              48
              sort_order
              DESCENDING
              source_name
              EM Portuguese
              display_type
              percentages
              task_version
              1
              task_display_type
              PERCENTAGES
              normalization_status
              normalized
            published_at
            2025-07-15T11:49:31.790Z
            candidate_class
            modelVersion
            source_revision
            b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
            publisher_anchor
            openai/gpt-4.1-2025-04-14
            metric_population
            51
            benchmark_evaluation
            true
            task_metadata_source
            benchmarkVersion
            candidate_metadata_source
            benchmarkVersionMappings
            evaluated at
            2025-06-16T00:00:00.000Z
            source model id
            GPT-4.1
            confidence lower
            0.3666664665082126
            confidence upper
            0.4893335334917874
            Original result ↗

            Kaggle Benchmarks

            39.2%

            source id
            kaggleBenchmarks
            leaderboard name
            MultiLoKo French · EM French
            dimension
            reasoning
            metric
            MultiLoKo French · EM French
            rank
            11
            aggregation scope
            kaggle
            true
            status
            published
            license
            Apache-2.0
            direction
            higherIsBetter
            conditions
            task
            id
            36
            name
            EM French
            version
            1
            sort_order
            DESCENDING
            display_type
            percentages
            benchmark
            id
            59
            name
            MultiLoKo French
            type
            INDIVIDUAL
            owner
            metaresearch
            version
            1
            categories
            • multilingual and cross-lingual capabilities
            • general knowledge and reasoning
            version_id
            45
            maintainer_tier
            Kaggle-maintained
            maintenance_level
            KAGGLE_MAINTAINED
            candidate
            candidate_class
            modelVersion
            record_kind
            aggregate
            attribution
            Kaggle · metaresearch · MultiLoKo French
            license_url
            https://www.apache.org/licenses/LICENSE-2.0
            metric_kind
            MultiLoKo French · EM French
            rank_method
            competition rank among reported evaluations in identical conditions, including unlinked observations
            source_file
            45/leaderboard.json
            source_page
            https://www.kaggle.com/benchmarks/metaresearch/multiloko-french/versions/1
            measurements
            • name
              EM French
              unit
              percent
              scale
              1
              metric
              MultiLoKo French · EM French
              result
              resultCase
              numericResult
              booleanResult
              false
              numericResult
              value
              0.392
              standardDeviation
              0
              confidenceInterval
              0.06051637561814
              hasStandardDeviation
              false
              hasConfidenceInterval
              true
              confidenceIntervalNullable
              0.06051637561814
              hasUnevenConfidenceInterval
              false
              taskVersionId
              0
              evaluationDate
              2025-06-16T00:00:00Z
              hasBooleanResult
              false
              hasNumericResult
              true
              hasTaskVersionId
              false
              hasEvaluationDate
              true
              numericResultNullable
              value
              0.392
              standardDeviation
              0
              confidenceInterval
              0.06051637561814
              hasStandardDeviation
              false
              hasConfidenceInterval
              true
              confidenceIntervalNullable
              0.06051637561814
              hasUnevenConfidenceInterval
              false
              hasNumericResultPublic
              false
              customAdditionalResults
                hasNumericResultPrivate
                false
                task_id
                36
                sort_order
                DESCENDING
                source_name
                EM French
                display_type
                percentages
                task_version
                1
                task_display_type
                PERCENTAGES
                normalization_status
                normalized
              published_at
              2025-07-15T11:49:31.790Z
              candidate_class
              modelVersion
              source_revision
              b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
              publisher_anchor
              openai/gpt-4.1-2025-04-14
              metric_population
              51
              benchmark_evaluation
              true
              task_metadata_source
              benchmarkVersion
              candidate_metadata_source
              benchmarkVersionMappings
              evaluated at
              2025-06-16T00:00:00.000Z
              source model id
              GPT-4.1
              confidence lower
              0.33148362438186
              confidence upper
              0.45251637561814
              Original result ↗

              Kaggle Benchmarks

              35.6%

              source id
              kaggleBenchmarks
              leaderboard name
              MultiLoKo German · EM German
              dimension
              reasoning
              metric
              MultiLoKo German · EM German
              rank
              11
              aggregation scope
              kaggle
              true
              status
              published
              license
              Apache-2.0
              direction
              higherIsBetter
              conditions
              task
              id
              37
              name
              EM German
              version
              1
              sort_order
              DESCENDING
              display_type
              percentages
              benchmark
              id
              60
              name
              MultiLoKo German
              type
              INDIVIDUAL
              owner
              metaresearch
              version
              1
              categories
              • multilingual and cross-lingual capabilities
              • general knowledge and reasoning
              version_id
              46
              maintainer_tier
              Kaggle-maintained
              maintenance_level
              KAGGLE_MAINTAINED
              candidate
              candidate_class
              modelVersion
              record_kind
              aggregate
              attribution
              Kaggle · metaresearch · MultiLoKo German
              license_url
              https://www.apache.org/licenses/LICENSE-2.0
              metric_kind
              MultiLoKo German · EM German
              rank_method
              competition rank among reported evaluations in identical conditions, including unlinked observations
              source_file
              46/leaderboard.json
              source_page
              https://www.kaggle.com/benchmarks/metaresearch/multiloko-german/versions/1
              measurements
              • name
                EM German
                unit
                percent
                scale
                1
                metric
                MultiLoKo German · EM German
                result
                resultCase
                numericResult
                booleanResult
                false
                numericResult
                value
                0.356
                standardDeviation
                0
                confidenceInterval
                0.0593534570203831
                hasStandardDeviation
                false
                hasConfidenceInterval
                true
                confidenceIntervalNullable
                0.0593534570203831
                hasUnevenConfidenceInterval
                false
                taskVersionId
                0
                evaluationDate
                2025-06-16T00:00:00Z
                hasBooleanResult
                false
                hasNumericResult
                true
                hasTaskVersionId
                false
                hasEvaluationDate
                true
                numericResultNullable
                value
                0.356
                standardDeviation
                0
                confidenceInterval
                0.0593534570203831
                hasStandardDeviation
                false
                hasConfidenceInterval
                true
                confidenceIntervalNullable
                0.0593534570203831
                hasUnevenConfidenceInterval
                false
                hasNumericResultPublic
                false
                customAdditionalResults
                  hasNumericResultPrivate
                  false
                  task_id
                  37
                  sort_order
                  DESCENDING
                  source_name
                  EM German
                  display_type
                  percentages
                  task_version
                  1
                  task_display_type
                  PERCENTAGES
                  normalization_status
                  normalized
                published_at
                2025-07-15T11:49:31.790Z
                candidate_class
                modelVersion
                source_revision
                b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                publisher_anchor
                openai/gpt-4.1-2025-04-14
                metric_population
                51
                benchmark_evaluation
                true
                task_metadata_source
                benchmarkVersion
                candidate_metadata_source
                benchmarkVersionMappings
                evaluated at
                2025-06-16T00:00:00.000Z
                source model id
                GPT-4.1
                confidence lower
                0.2966465429796169
                confidence upper
                0.41535345702038307
                Original result ↗

                Kaggle Benchmarks

                30%

                source id
                kaggleBenchmarks
                leaderboard name
                MultiLoKo Indonesian · EM Indonesian
                dimension
                reasoning
                metric
                MultiLoKo Indonesian · EM Indonesian
                rank
                11
                aggregation scope
                kaggle
                true
                status
                published
                license
                Apache-2.0
                direction
                higherIsBetter
                conditions
                task
                id
                40
                name
                EM Indonesian
                version
                1
                sort_order
                DESCENDING
                display_type
                percentages
                benchmark
                id
                63
                name
                MultiLoKo Indonesian
                type
                INDIVIDUAL
                owner
                metaresearch
                version
                1
                categories
                • multilingual and cross-lingual capabilities
                • general knowledge and reasoning
                version_id
                49
                maintainer_tier
                Kaggle-maintained
                maintenance_level
                KAGGLE_MAINTAINED
                candidate
                candidate_class
                modelVersion
                record_kind
                aggregate
                attribution
                Kaggle · metaresearch · MultiLoKo Indonesian
                license_url
                https://www.apache.org/licenses/LICENSE-2.0
                metric_kind
                MultiLoKo Indonesian · EM Indonesian
                rank_method
                competition rank among reported evaluations in identical conditions, including unlinked observations
                source_file
                49/leaderboard.json
                source_page
                https://www.kaggle.com/benchmarks/metaresearch/multiloko-indonesian/versions/1
                measurements
                • name
                  EM Indonesian
                  unit
                  percent
                  scale
                  1
                  metric
                  MultiLoKo Indonesian · EM Indonesian
                  result
                  resultCase
                  numericResult
                  booleanResult
                  false
                  numericResult
                  value
                  0.3
                  standardDeviation
                  0
                  confidenceInterval
                  0.056805153017865
                  hasStandardDeviation
                  false
                  hasConfidenceInterval
                  true
                  confidenceIntervalNullable
                  0.056805153017865
                  hasUnevenConfidenceInterval
                  false
                  taskVersionId
                  0
                  evaluationDate
                  2025-06-16T00:00:00Z
                  hasBooleanResult
                  false
                  hasNumericResult
                  true
                  hasTaskVersionId
                  false
                  hasEvaluationDate
                  true
                  numericResultNullable
                  value
                  0.3
                  standardDeviation
                  0
                  confidenceInterval
                  0.056805153017865
                  hasStandardDeviation
                  false
                  hasConfidenceInterval
                  true
                  confidenceIntervalNullable
                  0.056805153017865
                  hasUnevenConfidenceInterval
                  false
                  hasNumericResultPublic
                  false
                  customAdditionalResults
                    hasNumericResultPrivate
                    false
                    task_id
                    40
                    sort_order
                    DESCENDING
                    source_name
                    EM Indonesian
                    display_type
                    percentages
                    task_version
                    1
                    task_display_type
                    PERCENTAGES
                    normalization_status
                    normalized
                  published_at
                  2025-07-15T11:49:31.790Z
                  candidate_class
                  modelVersion
                  source_revision
                  b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                  publisher_anchor
                  openai/gpt-4.1-2025-04-14
                  metric_population
                  51
                  benchmark_evaluation
                  true
                  task_metadata_source
                  benchmarkVersion
                  candidate_metadata_source
                  benchmarkVersionMappings
                  evaluated at
                  2025-06-16T00:00:00.000Z
                  source model id
                  GPT-4.1
                  confidence lower
                  0.243194846982135
                  confidence upper
                  0.356805153017865
                  Original result ↗

                  Kaggle Benchmarks

                  27.2%

                  source id
                  kaggleBenchmarks
                  leaderboard name
                  MultiLoKo Korean · EM Korean
                  dimension
                  reasoning
                  metric
                  MultiLoKo Korean · EM Korean
                  rank
                  11
                  aggregation scope
                  kaggle
                  true
                  status
                  published
                  license
                  Apache-2.0
                  direction
                  higherIsBetter
                  conditions
                  task
                  id
                  44
                  name
                  EM Korean
                  version
                  1
                  sort_order
                  DESCENDING
                  display_type
                  percentages
                  benchmark
                  id
                  67
                  name
                  MultiLoKo Korean
                  type
                  INDIVIDUAL
                  owner
                  metaresearch
                  version
                  1
                  categories
                  • multilingual and cross-lingual capabilities
                  • general knowledge and reasoning
                  version_id
                  53
                  maintainer_tier
                  Kaggle-maintained
                  maintenance_level
                  KAGGLE_MAINTAINED
                  candidate
                  candidate_class
                  modelVersion
                  record_kind
                  aggregate
                  attribution
                  Kaggle · metaresearch · MultiLoKo Korean
                  license_url
                  https://www.apache.org/licenses/LICENSE-2.0
                  metric_kind
                  MultiLoKo Korean · EM Korean
                  rank_method
                  competition rank among reported evaluations in identical conditions, including unlinked observations
                  source_file
                  53/leaderboard.json
                  source_page
                  https://www.kaggle.com/benchmarks/metaresearch/multiloko-korean/versions/1
                  measurements
                  • name
                    EM Korean
                    unit
                    percent
                    scale
                    1
                    metric
                    MultiLoKo Korean · EM Korean
                    result
                    resultCase
                    numericResult
                    booleanResult
                    false
                    numericResult
                    value
                    0.272
                    standardDeviation
                    0
                    confidenceInterval
                    0.05516050434282
                    hasStandardDeviation
                    false
                    hasConfidenceInterval
                    true
                    confidenceIntervalNullable
                    0.05516050434282
                    hasUnevenConfidenceInterval
                    false
                    taskVersionId
                    0
                    evaluationDate
                    2025-06-16T00:00:00Z
                    hasBooleanResult
                    false
                    hasNumericResult
                    true
                    hasTaskVersionId
                    false
                    hasEvaluationDate
                    true
                    numericResultNullable
                    value
                    0.272
                    standardDeviation
                    0
                    confidenceInterval
                    0.05516050434282
                    hasStandardDeviation
                    false
                    hasConfidenceInterval
                    true
                    confidenceIntervalNullable
                    0.05516050434282
                    hasUnevenConfidenceInterval
                    false
                    hasNumericResultPublic
                    false
                    customAdditionalResults
                      hasNumericResultPrivate
                      false
                      task_id
                      44
                      sort_order
                      DESCENDING
                      source_name
                      EM Korean
                      display_type
                      percentages
                      task_version
                      1
                      task_display_type
                      PERCENTAGES
                      normalization_status
                      normalized
                    published_at
                    2025-07-15T11:49:31.790Z
                    candidate_class
                    modelVersion
                    source_revision
                    b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                    publisher_anchor
                    openai/gpt-4.1-2025-04-14
                    metric_population
                    51
                    benchmark_evaluation
                    true
                    task_metadata_source
                    benchmarkVersion
                    candidate_metadata_source
                    benchmarkVersionMappings
                    evaluated at
                    2025-06-16T00:00:00.000Z
                    source model id
                    GPT-4.1
                    confidence lower
                    0.21683949565718003
                    confidence upper
                    0.32716050434282
                    Original result ↗

                    Kaggle Benchmarks

                    24.8%

                    source id
                    kaggleBenchmarks
                    leaderboard name
                    MultiLoKo Polish · EM Polish
                    dimension
                    reasoning
                    metric
                    MultiLoKo Polish · EM Polish
                    rank
                    11
                    aggregation scope
                    kaggle
                    true
                    status
                    published
                    license
                    Apache-2.0
                    direction
                    higherIsBetter
                    conditions
                    task
                    id
                    47
                    name
                    EM Polish
                    version
                    1
                    sort_order
                    DESCENDING
                    display_type
                    percentages
                    benchmark
                    id
                    70
                    name
                    MultiLoKo Polish
                    type
                    INDIVIDUAL
                    owner
                    metaresearch
                    version
                    1
                    categories
                    • multilingual and cross-lingual capabilities
                    • general knowledge and reasoning
                    version_id
                    56
                    maintainer_tier
                    Kaggle-maintained
                    maintenance_level
                    KAGGLE_MAINTAINED
                    candidate
                    candidate_class
                    modelVersion
                    record_kind
                    aggregate
                    attribution
                    Kaggle · metaresearch · MultiLoKo Polish
                    license_url
                    https://www.apache.org/licenses/LICENSE-2.0
                    metric_kind
                    MultiLoKo Polish · EM Polish
                    rank_method
                    competition rank among reported evaluations in identical conditions, including unlinked observations
                    source_file
                    56/leaderboard.json
                    source_page
                    https://www.kaggle.com/benchmarks/metaresearch/multiloko-polish/versions/1
                    measurements
                    • name
                      EM Polish
                      unit
                      percent
                      scale
                      1
                      metric
                      MultiLoKo Polish · EM Polish
                      result
                      resultCase
                      numericResult
                      booleanResult
                      false
                      numericResult
                      value
                      0.248
                      standardDeviation
                      0
                      confidenceInterval
                      0.0535319233438953
                      hasStandardDeviation
                      false
                      hasConfidenceInterval
                      true
                      confidenceIntervalNullable
                      0.0535319233438953
                      hasUnevenConfidenceInterval
                      false
                      taskVersionId
                      0
                      evaluationDate
                      2025-06-16T00:00:00Z
                      hasBooleanResult
                      false
                      hasNumericResult
                      true
                      hasTaskVersionId
                      false
                      hasEvaluationDate
                      true
                      numericResultNullable
                      value
                      0.248
                      standardDeviation
                      0
                      confidenceInterval
                      0.0535319233438953
                      hasStandardDeviation
                      false
                      hasConfidenceInterval
                      true
                      confidenceIntervalNullable
                      0.0535319233438953
                      hasUnevenConfidenceInterval
                      false
                      hasNumericResultPublic
                      false
                      customAdditionalResults
                        hasNumericResultPrivate
                        false
                        task_id
                        47
                        sort_order
                        DESCENDING
                        source_name
                        EM Polish
                        display_type
                        percentages
                        task_version
                        1
                        task_display_type
                        PERCENTAGES
                        normalization_status
                        normalized
                      published_at
                      2025-07-15T11:49:31.790Z
                      candidate_class
                      modelVersion
                      source_revision
                      b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                      publisher_anchor
                      openai/gpt-4.1-2025-04-14
                      metric_population
                      51
                      benchmark_evaluation
                      true
                      task_metadata_source
                      benchmarkVersion
                      candidate_metadata_source
                      benchmarkVersionMappings
                      evaluated at
                      2025-06-16T00:00:00.000Z
                      source model id
                      GPT-4.1
                      confidence lower
                      0.1944680766561047
                      confidence upper
                      0.3015319233438953
                      Original result ↗

                      LMArena

                      1,211.447

                      source id
                      lmarena
                      leaderboard name
                      LMArena Vision Style Control Captioning
                      dimension
                      multimodal
                      metric
                      Arena rating
                      rank
                      12
                      sample size
                      421
                      evaluated at
                      2026-11-09T00:00:00.000Z
                      source model id
                      GPT-4.1 (2025-04-14)
                      confidence lower
                      1179.251741524959
                      confidence upper
                      1243.6422216742246
                      Original result ↗

                      BFCL

                      88.69%

                      source id
                      bfcl
                      leaderboard name
                      BFCL Non-Live AST
                      dimension
                      toolUse
                      metric
                      Non-live AST accuracy
                      rank
                      12
                      Original result ↗

                      Kaggle Benchmarks

                      21.6%

                      source id
                      kaggleBenchmarks
                      leaderboard name
                      MultiLoKo Thai · EM Thai
                      dimension
                      reasoning
                      metric
                      MultiLoKo Thai · EM Thai
                      rank
                      12
                      aggregation scope
                      kaggle
                      true
                      status
                      published
                      license
                      Apache-2.0
                      direction
                      higherIsBetter
                      conditions
                      task
                      id
                      55
                      name
                      EM Thai
                      version
                      1
                      sort_order
                      DESCENDING
                      display_type
                      percentages
                      benchmark
                      id
                      78
                      name
                      MultiLoKo Thai
                      type
                      INDIVIDUAL
                      owner
                      metaresearch
                      version
                      1
                      categories
                      • multilingual and cross-lingual capabilities
                      • general knowledge and reasoning
                      version_id
                      64
                      maintainer_tier
                      Kaggle-maintained
                      maintenance_level
                      KAGGLE_MAINTAINED
                      candidate
                      candidate_class
                      modelVersion
                      record_kind
                      aggregate
                      attribution
                      Kaggle · metaresearch · MultiLoKo Thai
                      license_url
                      https://www.apache.org/licenses/LICENSE-2.0
                      metric_kind
                      MultiLoKo Thai · EM Thai
                      rank_method
                      competition rank among reported evaluations in identical conditions, including unlinked observations
                      source_file
                      64/leaderboard.json
                      source_page
                      https://www.kaggle.com/benchmarks/metaresearch/multiloko-thai/versions/1
                      measurements
                      • name
                        EM Thai
                        unit
                        percent
                        scale
                        1
                        metric
                        MultiLoKo Thai · EM Thai
                        result
                        resultCase
                        numericResult
                        booleanResult
                        false
                        numericResult
                        value
                        0.216
                        standardDeviation
                        0
                        confidenceInterval
                        0.0510109008950685
                        hasStandardDeviation
                        false
                        hasConfidenceInterval
                        true
                        confidenceIntervalNullable
                        0.0510109008950685
                        hasUnevenConfidenceInterval
                        false
                        taskVersionId
                        0
                        evaluationDate
                        2025-06-16T00:00:00Z
                        hasBooleanResult
                        false
                        hasNumericResult
                        true
                        hasTaskVersionId
                        false
                        hasEvaluationDate
                        true
                        numericResultNullable
                        value
                        0.216
                        standardDeviation
                        0
                        confidenceInterval
                        0.0510109008950685
                        hasStandardDeviation
                        false
                        hasConfidenceInterval
                        true
                        confidenceIntervalNullable
                        0.0510109008950685
                        hasUnevenConfidenceInterval
                        false
                        hasNumericResultPublic
                        false
                        customAdditionalResults
                          hasNumericResultPrivate
                          false
                          task_id
                          55
                          sort_order
                          DESCENDING
                          source_name
                          EM Thai
                          display_type
                          percentages
                          task_version
                          1
                          task_display_type
                          PERCENTAGES
                          normalization_status
                          normalized
                        published_at
                        2025-07-15T11:49:31.790Z
                        candidate_class
                        modelVersion
                        source_revision
                        b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                        publisher_anchor
                        openai/gpt-4.1-2025-04-14
                        metric_population
                        51
                        benchmark_evaluation
                        true
                        task_metadata_source
                        benchmarkVersion
                        candidate_metadata_source
                        benchmarkVersionMappings
                        evaluated at
                        2025-06-16T00:00:00.000Z
                        source model id
                        GPT-4.1
                        confidence lower
                        0.16498909910493148
                        confidence upper
                        0.2670109008950685
                        Original result ↗

                        Kaggle Benchmarks

                        16%

                        source id
                        kaggleBenchmarks
                        leaderboard name
                        MultiLoKo Farsi · EM Farsi
                        dimension
                        reasoning
                        metric
                        MultiLoKo Farsi · EM Farsi
                        rank
                        14
                        aggregation scope
                        kaggle
                        true
                        status
                        published
                        license
                        Apache-2.0
                        direction
                        higherIsBetter
                        conditions
                        task
                        id
                        35
                        name
                        EM Farsi
                        version
                        1
                        sort_order
                        DESCENDING
                        display_type
                        percentages
                        benchmark
                        id
                        58
                        name
                        MultiLoKo Farsi
                        type
                        INDIVIDUAL
                        owner
                        metaresearch
                        version
                        1
                        categories
                        • multilingual and cross-lingual capabilities
                        • general knowledge and reasoning
                        version_id
                        44
                        maintainer_tier
                        Kaggle-maintained
                        maintenance_level
                        KAGGLE_MAINTAINED
                        candidate
                        candidate_class
                        modelVersion
                        record_kind
                        aggregate
                        attribution
                        Kaggle · metaresearch · MultiLoKo Farsi
                        license_url
                        https://www.apache.org/licenses/LICENSE-2.0
                        metric_kind
                        MultiLoKo Farsi · EM Farsi
                        rank_method
                        competition rank among reported evaluations in identical conditions, including unlinked observations
                        source_file
                        44/leaderboard.json
                        source_page
                        https://www.kaggle.com/benchmarks/metaresearch/multiloko-farsi/versions/1
                        measurements
                        • name
                          EM Farsi
                          unit
                          percent
                          scale
                          1
                          metric
                          MultiLoKo Farsi · EM Farsi
                          result
                          resultCase
                          numericResult
                          booleanResult
                          false
                          numericResult
                          value
                          0.16
                          standardDeviation
                          0
                          confidenceInterval
                          0.045444122414292
                          hasStandardDeviation
                          false
                          hasConfidenceInterval
                          true
                          confidenceIntervalNullable
                          0.045444122414292
                          hasUnevenConfidenceInterval
                          false
                          taskVersionId
                          0
                          evaluationDate
                          2025-06-16T00:00:00Z
                          hasBooleanResult
                          false
                          hasNumericResult
                          true
                          hasTaskVersionId
                          false
                          hasEvaluationDate
                          true
                          numericResultNullable
                          value
                          0.16
                          standardDeviation
                          0
                          confidenceInterval
                          0.045444122414292
                          hasStandardDeviation
                          false
                          hasConfidenceInterval
                          true
                          confidenceIntervalNullable
                          0.045444122414292
                          hasUnevenConfidenceInterval
                          false
                          hasNumericResultPublic
                          false
                          customAdditionalResults
                            hasNumericResultPrivate
                            false
                            task_id
                            35
                            sort_order
                            DESCENDING
                            source_name
                            EM Farsi
                            display_type
                            percentages
                            task_version
                            1
                            task_display_type
                            PERCENTAGES
                            normalization_status
                            normalized
                          published_at
                          2025-07-15T11:49:31.790Z
                          candidate_class
                          modelVersion
                          source_revision
                          b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                          publisher_anchor
                          openai/gpt-4.1-2025-04-14
                          metric_population
                          50
                          benchmark_evaluation
                          true
                          task_metadata_source
                          benchmarkVersion
                          candidate_metadata_source
                          benchmarkVersionMappings
                          evaluated at
                          2025-06-16T00:00:00.000Z
                          source model id
                          GPT-4.1
                          confidence lower
                          0.11455587758570801
                          confidence upper
                          0.205444122414292
                          Original result ↗

                          Kaggle Benchmarks

                          4%

                          source id
                          kaggleBenchmarks
                          leaderboard name
                          MultiLoKo Urdu · EM Urdu
                          dimension
                          reasoning
                          metric
                          MultiLoKo Urdu · EM Urdu
                          rank
                          14
                          aggregation scope
                          kaggle
                          true
                          status
                          published
                          license
                          Apache-2.0
                          direction
                          higherIsBetter
                          conditions
                          task
                          id
                          58
                          name
                          EM Urdu
                          version
                          1
                          sort_order
                          DESCENDING
                          display_type
                          percentages
                          benchmark
                          id
                          81
                          name
                          MultiLoKo Urdu
                          type
                          INDIVIDUAL
                          owner
                          metaresearch
                          version
                          1
                          categories
                          • multilingual and cross-lingual capabilities
                          • general knowledge and reasoning
                          version_id
                          67
                          maintainer_tier
                          Kaggle-maintained
                          maintenance_level
                          KAGGLE_MAINTAINED
                          candidate
                          candidate_class
                          modelVersion
                          record_kind
                          aggregate
                          attribution
                          Kaggle · metaresearch · MultiLoKo Urdu
                          license_url
                          https://www.apache.org/licenses/LICENSE-2.0
                          metric_kind
                          MultiLoKo Urdu · EM Urdu
                          rank_method
                          competition rank among reported evaluations in identical conditions, including unlinked observations
                          source_file
                          67/leaderboard.json
                          source_page
                          https://www.kaggle.com/benchmarks/metaresearch/multiloko-urdu/versions/1
                          measurements
                          • name
                            EM Urdu
                            unit
                            percent
                            scale
                            1
                            metric
                            MultiLoKo Urdu · EM Urdu
                            result
                            resultCase
                            numericResult
                            booleanResult
                            false
                            numericResult
                            value
                            0.04
                            standardDeviation
                            0
                            confidenceInterval
                            0.0242909051881278
                            hasStandardDeviation
                            false
                            hasConfidenceInterval
                            true
                            confidenceIntervalNullable
                            0.0242909051881278
                            hasUnevenConfidenceInterval
                            false
                            taskVersionId
                            0
                            evaluationDate
                            2025-06-16T00:00:00Z
                            hasBooleanResult
                            false
                            hasNumericResult
                            true
                            hasTaskVersionId
                            false
                            hasEvaluationDate
                            true
                            numericResultNullable
                            value
                            0.04
                            standardDeviation
                            0
                            confidenceInterval
                            0.0242909051881278
                            hasStandardDeviation
                            false
                            hasConfidenceInterval
                            true
                            confidenceIntervalNullable
                            0.0242909051881278
                            hasUnevenConfidenceInterval
                            false
                            hasNumericResultPublic
                            false
                            customAdditionalResults
                              hasNumericResultPrivate
                              false
                              task_id
                              58
                              sort_order
                              DESCENDING
                              source_name
                              EM Urdu
                              display_type
                              percentages
                              task_version
                              1
                              task_display_type
                              PERCENTAGES
                              normalization_status
                              normalized
                            published_at
                            2025-07-15T11:49:31.790Z
                            candidate_class
                            modelVersion
                            source_revision
                            b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                            publisher_anchor
                            openai/gpt-4.1-2025-04-14
                            metric_population
                            51
                            benchmark_evaluation
                            true
                            task_metadata_source
                            benchmarkVersion
                            candidate_metadata_source
                            benchmarkVersionMappings
                            evaluated at
                            2025-06-16T00:00:00.000Z
                            source model id
                            GPT-4.1
                            confidence lower
                            0.0157090948118722
                            confidence upper
                            0.0642909051881278
                            Original result ↗

                            Kaggle Benchmarks

                            35.6%

                            source id
                            kaggleBenchmarks
                            leaderboard name
                            MultiLoKo Russian · EM Russian
                            dimension
                            reasoning
                            metric
                            MultiLoKo Russian · EM Russian
                            rank
                            15
                            aggregation scope
                            kaggle
                            true
                            status
                            published
                            license
                            Apache-2.0
                            direction
                            higherIsBetter
                            conditions
                            task
                            id
                            50
                            name
                            EM Russian
                            version
                            1
                            sort_order
                            DESCENDING
                            display_type
                            percentages
                            benchmark
                            id
                            73
                            name
                            MultiLoKo Russian
                            type
                            INDIVIDUAL
                            owner
                            metaresearch
                            version
                            1
                            categories
                            • multilingual and cross-lingual capabilities
                            • general knowledge and reasoning
                            version_id
                            59
                            maintainer_tier
                            Kaggle-maintained
                            maintenance_level
                            KAGGLE_MAINTAINED
                            candidate
                            candidate_class
                            modelVersion
                            record_kind
                            aggregate
                            attribution
                            Kaggle · metaresearch · MultiLoKo Russian
                            license_url
                            https://www.apache.org/licenses/LICENSE-2.0
                            metric_kind
                            MultiLoKo Russian · EM Russian
                            rank_method
                            competition rank among reported evaluations in identical conditions, including unlinked observations
                            source_file
                            59/leaderboard.json
                            source_page
                            https://www.kaggle.com/benchmarks/metaresearch/multiloko-russian/versions/1
                            measurements
                            • name
                              EM Russian
                              unit
                              percent
                              scale
                              1
                              metric
                              MultiLoKo Russian · EM Russian
                              result
                              resultCase
                              numericResult
                              booleanResult
                              false
                              numericResult
                              value
                              0.356
                              standardDeviation
                              0
                              confidenceInterval
                              0.0593534570203831
                              hasStandardDeviation
                              false
                              hasConfidenceInterval
                              true
                              confidenceIntervalNullable
                              0.0593534570203831
                              hasUnevenConfidenceInterval
                              false
                              taskVersionId
                              0
                              evaluationDate
                              2025-06-16T00:00:00Z
                              hasBooleanResult
                              false
                              hasNumericResult
                              true
                              hasTaskVersionId
                              false
                              hasEvaluationDate
                              true
                              numericResultNullable
                              value
                              0.356
                              standardDeviation
                              0
                              confidenceInterval
                              0.0593534570203831
                              hasStandardDeviation
                              false
                              hasConfidenceInterval
                              true
                              confidenceIntervalNullable
                              0.0593534570203831
                              hasUnevenConfidenceInterval
                              false
                              hasNumericResultPublic
                              false
                              customAdditionalResults
                                hasNumericResultPrivate
                                false
                                task_id
                                50
                                sort_order
                                DESCENDING
                                source_name
                                EM Russian
                                display_type
                                percentages
                                task_version
                                1
                                task_display_type
                                PERCENTAGES
                                normalization_status
                                normalized
                              published_at
                              2025-07-15T11:49:31.790Z
                              candidate_class
                              modelVersion
                              source_revision
                              b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                              publisher_anchor
                              openai/gpt-4.1-2025-04-14
                              metric_population
                              51
                              benchmark_evaluation
                              true
                              task_metadata_source
                              benchmarkVersion
                              candidate_metadata_source
                              benchmarkVersionMappings
                              evaluated at
                              2025-06-16T00:00:00.000Z
                              source model id
                              GPT-4.1
                              confidence lower
                              0.2966465429796169
                              confidence upper
                              0.41535345702038307
                              Original result ↗

                              Kaggle Benchmarks

                              35.6%

                              source id
                              kaggleBenchmarks
                              leaderboard name
                              MultiLoKo Simplified Mandarin · EM Simplified Mandarin
                              dimension
                              reasoning
                              metric
                              MultiLoKo Simplified Mandarin · EM Simplified Mandarin
                              rank
                              15
                              aggregation scope
                              kaggle
                              true
                              status
                              published
                              license
                              Apache-2.0
                              direction
                              higherIsBetter
                              conditions
                              task
                              id
                              51
                              name
                              EM Simplified Mandarin
                              version
                              1
                              sort_order
                              DESCENDING
                              display_type
                              percentages
                              benchmark
                              id
                              74
                              name
                              MultiLoKo Simplified Mandarin
                              type
                              INDIVIDUAL
                              owner
                              metaresearch
                              version
                              1
                              categories
                              • multilingual and cross-lingual capabilities
                              • general knowledge and reasoning
                              version_id
                              60
                              maintainer_tier
                              Kaggle-maintained
                              maintenance_level
                              KAGGLE_MAINTAINED
                              candidate
                              candidate_class
                              modelVersion
                              record_kind
                              aggregate
                              attribution
                              Kaggle · metaresearch · MultiLoKo Simplified Mandarin
                              license_url
                              https://www.apache.org/licenses/LICENSE-2.0
                              metric_kind
                              MultiLoKo Simplified Mandarin · EM Simplified Mandarin
                              rank_method
                              competition rank among reported evaluations in identical conditions, including unlinked observations
                              source_file
                              60/leaderboard.json
                              source_page
                              https://www.kaggle.com/benchmarks/metaresearch/multiloko-simplified-mandarin/versions/1
                              measurements
                              • name
                                EM Simplified Mandarin
                                unit
                                percent
                                scale
                                1
                                metric
                                MultiLoKo Simplified Mandarin · EM Simplified Mandarin
                                result
                                resultCase
                                numericResult
                                booleanResult
                                false
                                numericResult
                                value
                                0.356
                                standardDeviation
                                0
                                confidenceInterval
                                0.0593534570203831
                                hasStandardDeviation
                                false
                                hasConfidenceInterval
                                true
                                confidenceIntervalNullable
                                0.0593534570203831
                                hasUnevenConfidenceInterval
                                false
                                taskVersionId
                                0
                                evaluationDate
                                2025-06-16T00:00:00Z
                                hasBooleanResult
                                false
                                hasNumericResult
                                true
                                hasTaskVersionId
                                false
                                hasEvaluationDate
                                true
                                numericResultNullable
                                value
                                0.356
                                standardDeviation
                                0
                                confidenceInterval
                                0.0593534570203831
                                hasStandardDeviation
                                false
                                hasConfidenceInterval
                                true
                                confidenceIntervalNullable
                                0.0593534570203831
                                hasUnevenConfidenceInterval
                                false
                                hasNumericResultPublic
                                false
                                customAdditionalResults
                                  hasNumericResultPrivate
                                  false
                                  task_id
                                  51
                                  sort_order
                                  DESCENDING
                                  source_name
                                  EM Simplified Mandarin
                                  display_type
                                  percentages
                                  task_version
                                  1
                                  task_display_type
                                  PERCENTAGES
                                  normalization_status
                                  normalized
                                published_at
                                2025-07-15T11:49:31.790Z
                                candidate_class
                                modelVersion
                                source_revision
                                b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                publisher_anchor
                                openai/gpt-4.1-2025-04-14
                                metric_population
                                51
                                benchmark_evaluation
                                true
                                task_metadata_source
                                benchmarkVersion
                                candidate_metadata_source
                                benchmarkVersionMappings
                                evaluated at
                                2025-06-16T00:00:00.000Z
                                source model id
                                GPT-4.1
                                confidence lower
                                0.2966465429796169
                                confidence upper
                                0.41535345702038307
                                Original result ↗

                                Kaggle Benchmarks

                                21.6%

                                source id
                                kaggleBenchmarks
                                leaderboard name
                                MultiLoKo Cantonese · EM Cantonese
                                dimension
                                reasoning
                                metric
                                MultiLoKo Cantonese · EM Cantonese
                                rank
                                15
                                aggregation scope
                                kaggle
                                true
                                status
                                published
                                license
                                Apache-2.0
                                direction
                                higherIsBetter
                                conditions
                                task
                                id
                                32
                                name
                                EM Cantonese
                                version
                                1
                                sort_order
                                DESCENDING
                                display_type
                                percentages
                                benchmark
                                id
                                55
                                name
                                MultiLoKo Cantonese
                                type
                                INDIVIDUAL
                                owner
                                metaresearch
                                version
                                1
                                categories
                                • multilingual and cross-lingual capabilities
                                • general knowledge and reasoning
                                version_id
                                41
                                maintainer_tier
                                Kaggle-maintained
                                maintenance_level
                                KAGGLE_MAINTAINED
                                candidate
                                candidate_class
                                modelVersion
                                record_kind
                                aggregate
                                attribution
                                Kaggle · metaresearch · MultiLoKo Cantonese
                                license_url
                                https://www.apache.org/licenses/LICENSE-2.0
                                metric_kind
                                MultiLoKo Cantonese · EM Cantonese
                                rank_method
                                competition rank among reported evaluations in identical conditions, including unlinked observations
                                source_file
                                41/leaderboard.json
                                source_page
                                https://www.kaggle.com/benchmarks/metaresearch/multiloko-cantonese/versions/1
                                measurements
                                • name
                                  EM Cantonese
                                  unit
                                  percent
                                  scale
                                  1
                                  metric
                                  MultiLoKo Cantonese · EM Cantonese
                                  result
                                  resultCase
                                  numericResult
                                  booleanResult
                                  false
                                  numericResult
                                  value
                                  0.216
                                  standardDeviation
                                  0
                                  confidenceInterval
                                  0.0510109008950685
                                  hasStandardDeviation
                                  false
                                  hasConfidenceInterval
                                  true
                                  confidenceIntervalNullable
                                  0.0510109008950685
                                  hasUnevenConfidenceInterval
                                  false
                                  taskVersionId
                                  0
                                  evaluationDate
                                  2025-06-16T00:00:00Z
                                  hasBooleanResult
                                  false
                                  hasNumericResult
                                  true
                                  hasTaskVersionId
                                  false
                                  hasEvaluationDate
                                  true
                                  numericResultNullable
                                  value
                                  0.216
                                  standardDeviation
                                  0
                                  confidenceInterval
                                  0.0510109008950685
                                  hasStandardDeviation
                                  false
                                  hasConfidenceInterval
                                  true
                                  confidenceIntervalNullable
                                  0.0510109008950685
                                  hasUnevenConfidenceInterval
                                  false
                                  hasNumericResultPublic
                                  false
                                  customAdditionalResults
                                    hasNumericResultPrivate
                                    false
                                    task_id
                                    32
                                    sort_order
                                    DESCENDING
                                    source_name
                                    EM Cantonese
                                    display_type
                                    percentages
                                    task_version
                                    1
                                    task_display_type
                                    PERCENTAGES
                                    normalization_status
                                    normalized
                                  published_at
                                  2025-07-15T11:49:31.790Z
                                  candidate_class
                                  modelVersion
                                  source_revision
                                  b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                  publisher_anchor
                                  openai/gpt-4.1-2025-04-14
                                  metric_population
                                  51
                                  benchmark_evaluation
                                  true
                                  task_metadata_source
                                  benchmarkVersion
                                  candidate_metadata_source
                                  benchmarkVersionMappings
                                  evaluated at
                                  2025-06-16T00:00:00.000Z
                                  source model id
                                  GPT-4.1
                                  confidence lower
                                  0.16498909910493148
                                  confidence upper
                                  0.2670109008950685
                                  Original result ↗

                                  LMArena

                                  1,222.903

                                  source id
                                  lmarena
                                  leaderboard name
                                  LMArena Vision Creative Writing
                                  dimension
                                  multimodal
                                  metric
                                  Arena rating
                                  rank
                                  16
                                  sample size
                                  1432
                                  evaluated at
                                  2026-01-09T00:00:00.000Z
                                  source model id
                                  gpt-4.1-2025-04-14
                                  confidence lower
                                  1206.6471290550458
                                  confidence upper
                                  1239.1595263905335
                                  Original result ↗

                                  Published prices

                                  1–20 / 36

                                  gpt-4.1 ↗

                                  $0.40

                                  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-4.1 ↗

                                  $0.00

                                  Inference provider
                                  cheaperInference
                                  Platform
                                  Cheaper Inference
                                  Unit
                                  cache_write_tokens_per_million
                                  Currency
                                  USD
                                  Billing conditions
                                  zdr
                                  false
                                  protocol
                                  chat_completions
                                  service_tier
                                  standard
                                  Billing label
                                  Cache write, 5 minutes (per 1M)

                                  gpt-4.1 ↗

                                  $1.61

                                  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-4.1 ↗

                                  $6.46

                                  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)

                                  openai/gpt-4.1 ↗

                                  $0.50

                                  Inference provider
                                  cloudflareWorkersAI
                                  Platform
                                  OpenAI
                                  Unit
                                  cache_read_tokens_per_million
                                  Currency
                                  USD
                                  Billing conditions
                                  Billing label
                                  Cached input tokens (per 1M)
                                  Pricing via
                                  Cloudflare AI Gateway

                                  openai/gpt-4.1 ↗

                                  $2.00

                                  Inference provider
                                  cloudflareWorkersAI
                                  Platform
                                  OpenAI
                                  Unit
                                  input_tokens_per_million
                                  Currency
                                  USD
                                  Billing conditions
                                  Billing label
                                  Input tokens (per 1M)
                                  Pricing via
                                  Cloudflare AI Gateway

                                  openai/gpt-4.1 ↗

                                  $8.00

                                  Inference provider
                                  cloudflareWorkersAI
                                  Platform
                                  OpenAI
                                  Unit
                                  output_tokens_per_million
                                  Currency
                                  USD
                                  Billing conditions
                                  Billing label
                                  Output tokens (per 1M)
                                  Pricing via
                                  Cloudflare AI Gateway

                                  openai/gpt-4.1 ↗

                                  $0.50

                                  Inference provider
                                  openRouter
                                  Platform
                                  OpenRouter
                                  Unit
                                  cache_read_tokens_per_million
                                  Currency
                                  USD
                                  Billing conditions

                                  openai/gpt-4.1 ↗

                                  $2.00

                                  Inference provider
                                  openRouter
                                  Platform
                                  OpenRouter
                                  Unit
                                  input_tokens_per_million
                                  Currency
                                  USD
                                  Billing conditions

                                  openai/gpt-4.1 ↗

                                  $8.00

                                  Inference provider
                                  openRouter
                                  Platform
                                  OpenRouter
                                  Unit
                                  output_tokens_per_million
                                  Currency
                                  USD
                                  Billing conditions

                                  openai/gpt-4.1 ↗

                                  $0.01

                                  Inference provider
                                  openRouter
                                  Platform
                                  OpenRouter
                                  Unit
                                  web_search
                                  Currency
                                  USD
                                  Billing conditions

                                  openai/gpt-4.1:batch ↗

                                  $0.25

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

                                  openai/gpt-4.1:batch ↗

                                  $1.00

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

                                  openai/gpt-4.1:batch ↗

                                  $4.00

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

                                  openai/gpt-4.1:batch ↗

                                  $0.01

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

                                  openai/gpt-4.1 ↗

                                  $0.50

                                  Inference provider
                                  vercelAIGatewayCatalog
                                  Platform
                                  azure
                                  Unit
                                  cache_read_tokens_per_million
                                  Currency
                                  USD
                                  Billing conditions
                                  endpoint
                                  azure | openai/gpt-4.1
                                  model_type
                                  language
                                  billing_scope
                                  via Vercel AI Gateway
                                  Billing label
                                  Cached input / 1M
                                  Pricing via
                                  Vercel AI Gateway

                                  openai/gpt-4.1 ↗

                                  $2.00

                                  Inference provider
                                  vercelAIGatewayCatalog
                                  Platform
                                  azure
                                  Unit
                                  input_tokens_per_million
                                  Currency
                                  USD
                                  Billing conditions
                                  endpoint
                                  azure | openai/gpt-4.1
                                  model_type
                                  language
                                  billing_scope
                                  via Vercel AI Gateway
                                  Billing label
                                  Input tokens / 1M
                                  Pricing via
                                  Vercel AI Gateway

                                  openai/gpt-4.1 ↗

                                  $8.00

                                  Inference provider
                                  vercelAIGatewayCatalog
                                  Platform
                                  azure
                                  Unit
                                  output_tokens_per_million
                                  Currency
                                  USD
                                  Billing conditions
                                  endpoint
                                  azure | openai/gpt-4.1
                                  model_type
                                  language
                                  billing_scope
                                  via Vercel AI Gateway
                                  Billing label
                                  Output tokens / 1M
                                  Pricing via
                                  Vercel AI Gateway

                                  openai/gpt-4.1 ↗

                                  $0.01

                                  Inference provider
                                  vercelAIGatewayCatalog
                                  Platform
                                  azure
                                  Unit
                                  request
                                  Currency
                                  USD
                                  Billing conditions
                                  charge
                                  web_search
                                  endpoint
                                  azure | openai/gpt-4.1
                                  model_type
                                  language
                                  billing_scope
                                  via Vercel AI Gateway
                                  Billing label
                                  Web search
                                  Pricing via
                                  Vercel AI Gateway

                                  openai/gpt-4.1 ↗

                                  $0.50

                                  Inference provider
                                  vercelAIGatewayCatalog
                                  Platform
                                  openai
                                  Unit
                                  cache_read_tokens_per_million
                                  Currency
                                  USD
                                  Billing conditions
                                  endpoint
                                  openai | openai/gpt-4.1
                                  model_type
                                  language
                                  billing_scope
                                  via Vercel AI Gateway
                                  Billing label
                                  Cached input / 1M
                                  Pricing via
                                  Vercel AI Gateway

                                  Provider specifications & access

                                  1–4 / 4

                                  OpenAI GPT-4.1 · azure-openai v2025-04-14 ↗

                                  source model id
                                  azure-openai/gpt-4.1@2025-04-14
                                  hosting
                                  foundry-managed-compute
                                  platforms
                                  • Microsoft Foundry
                                  license
                                  custom
                                  context length
                                  1048576
                                  max output tokens
                                  32768
                                  architecture
                                  input_modalities
                                  • text
                                  • image
                                  output_modalities
                                  • text
                                  capabilities
                                  • toolCalling

                                  gpt-4.1 ↗

                                  source model id
                                  gpt-4.1
                                  hosting
                                  gateway
                                  platforms
                                  • Cheaper Inference
                                  context length
                                  1047576
                                  max output tokens
                                  32768
                                  architecture
                                  input_modalities
                                  • text
                                  • image
                                  output_modalities
                                  • text
                                  capabilities
                                  • reasoning
                                  • structuredOutputs
                                  • toolCalling
                                  • visionInput
                                  • webSearch

                                  GPT-4.1 ↗

                                  source model id
                                  openai/gpt-4.1
                                  hosting
                                  third-party
                                  platforms
                                  • OpenAI
                                  context length
                                  1047576
                                  max output tokens
                                  32768
                                  architecture
                                  input_modalities
                                  • text
                                  output_modalities
                                  • text
                                  capabilities

                                    GPT-4.1 ↗

                                    source model id
                                    openai/gpt-4.1
                                    hosting
                                    vercel-gateway
                                    platforms
                                    • Vercel AI Gateway
                                    context length
                                    1047576
                                    max output tokens
                                    32768
                                    architecture
                                    input_modalities
                                    • text
                                    • image
                                    • pdf
                                    output_modalities
                                    • text
                                    capabilities
                                    • promptCaching
                                    • structuredOutputs
                                    • toolCalling
                                    • visionInput
                                    • webSearch

                                    Safety assessments

                                    1–1 / 1

                                    Foundation Model Transparency Index 2025 ↗

                                    35 / 100

                                    source id
                                    stanfordFMTI
                                    canonical model id
                                    openai/gpt-4.1-2025-04-14
                                    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

                                    1–14 / 14

                                    azureFoundry ↗

                                    field
                                    context_length
                                    value
                                    1048576
                                    normalized value
                                    1048576
                                    scope
                                    source-model
                                    source id
                                    azureFoundry
                                    confidence
                                    1

                                    cloudflareWorkersAI ↗

                                    field
                                    context_length
                                    value
                                    1047576
                                    normalized value
                                    1047576
                                    scope
                                    source-model
                                    source id
                                    cloudflareWorkersAI
                                    confidence
                                    1

                                    openRouter ↗

                                    field
                                    context_length
                                    value
                                    1047576
                                    normalized value
                                    1047576
                                    scope
                                    source-model
                                    source id
                                    openRouter
                                    confidence
                                    1

                                    openRouter ↗

                                    field
                                    context_length
                                    value
                                    1047576
                                    normalized value
                                    1047576
                                    scope
                                    source-model
                                    source id
                                    openRouter
                                    confidence
                                    1

                                    vercelAIGatewayCatalog ↗

                                    field
                                    context_length
                                    value
                                    1047576
                                    normalized value
                                    1047576
                                    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

                                    azureFoundry ↗

                                    field
                                    max_output_tokens
                                    value
                                    32768
                                    normalized value
                                    32768
                                    scope
                                    source-model
                                    source id
                                    azureFoundry
                                    confidence
                                    1

                                    cloudflareWorkersAI ↗

                                    field
                                    max_output_tokens
                                    value
                                    32768
                                    normalized value
                                    32768
                                    scope
                                    source-model
                                    source id
                                    cloudflareWorkersAI
                                    confidence
                                    1

                                    openRouter ↗

                                    field
                                    max_output_tokens
                                    value
                                    32768
                                    normalized value
                                    32768
                                    scope
                                    source-model
                                    source id
                                    openRouter
                                    confidence
                                    1

                                    openRouter ↗

                                    field
                                    max_output_tokens
                                    value
                                    32768
                                    normalized value
                                    32768
                                    scope
                                    source-model
                                    source id
                                    openRouter
                                    confidence
                                    1

                                    vercelAIGatewayCatalog ↗

                                    field
                                    max_output_tokens
                                    value
                                    32768
                                    normalized value
                                    32768
                                    scope
                                    source-model
                                    source id
                                    vercelAIGatewayCatalog
                                    confidence
                                    1

                                    azureFoundry ↗

                                    field
                                    knowledge_cutoff
                                    reported field
                                    training_data_cutoff
                                    value
                                    May 2024
                                    normalized value
                                    2024-05
                                    precision
                                    month
                                    scope
                                    source-model
                                    source id
                                    azureFoundry
                                    confidence
                                    1

                                    Original sources

                                    1–19 / 19

                                    OpenAI · Model reference ↗

                                    Microsoft Foundry · Model page ↗

                                    OpenRouter · Model page ↗

                                    OpenRouter · Model page ↗

                                    Vercel AI Gateway · Model page ↗

                                    Microsoft Foundry · Model documentation ↗

                                    GitHub · Source snapshot ↗

                                    api.cheaperinference.com · Source snapshot ↗

                                    Cloudflare AI · Catalog ↗

                                    GitHub · Catalog ↗

                                    GitHub · Catalog ↗

                                    Kaggle · Catalog ↗

                                    LMArena · Catalog ↗

                                    Microsoft Foundry · Catalog ↗

                                    OpenRouter · Catalog ↗

                                    OpenRouter · Catalog ↗

                                    Vercel AI Gateway · Catalog ↗

                                    gorilla.cs.berkeley.edu · Catalog ↗

                                    www.swebench.com · Catalog ↗

                                    Source links

                                    1–14 / 14

                                    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