OpenAI: GPT-5 Mini

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency a…

openai/gpt-5-mini-2025-08-07

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.

Specifications & capabilities

Input
text, image, file
Output
text
Context window · tokens
400000
Published model ID
gpt-5-mini-2025-08-07
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗

Evaluations

21–40 / 158

LMArena

1,173.352

source id
lmarena
leaderboard name
LMArena Vision Style Control Captioning
dimension
multimodal
metric
Arena rating
rank
21
sample size
282
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5 mini (High)
confidence lower
1130.3731573371101
confidence upper
1216.3310996888288
Original result ↗

OpenRouter Benchmarks

70.5%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Azure
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
22
sample size
200
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
4
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Azure
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T19:05:16.547Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
200
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.70499975
accuracy_std_dev
0.011902485735656231
cost_per_task_usd
0.13260128
output_tokens_per_task
55745.89
latency_seconds_per_task
477.32639
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
40
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-5-mini-2025-08-07
source model id
openai/gpt-5-mini-2025-08-07
Original result ↗

LMArena

1,181.311

source id
lmarena
leaderboard name
LMArena Vision Creative Writing
dimension
multimodal
metric
Arena rating
rank
26
sample size
1108
evaluated at
2026-01-09T00:00:00.000Z
source model id
gpt-5-mini-high
confidence lower
1163.143509390161
confidence upper
1199.478400457439
Original result ↗

LMArena

1,212.042

source id
lmarena
leaderboard name
LMArena Vision Style Control Entity Recognition
dimension
multimodal
metric
Arena rating
rank
28
sample size
280
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5 mini (High)
confidence lower
1171.5758579739063
confidence upper
1252.5074787290073
Original result ↗

Kaggle Benchmarks

188.042

source id
kaggleBenchmarks
leaderboard name
Dark Hex · Score
dimension
general
metric
Dark Hex · Score
rank
28
aggregation scope
kaggle
true
status
published
license
Apache-2.0
direction
higherIsBetter
conditions
task
id
33066
name
Score
version
1
sort_order
DESCENDING
display_type
counts
benchmark
id
5571
name
Dark Hex
type
GAME
owner
kaggle
version
1
categories
    version_id
    5594
    maintainer_tier
    Kaggle-published
    candidate
    candidate_class
    modelVersion
    collection
    kaggleGameArena
    record_kind
    aggregate
    game_arena
    true
    attribution
    Kaggle · kaggle · Dark Hex
    license_url
    https://www.apache.org/licenses/LICENSE-2.0
    metric_kind
    Dark Hex · Score
    rank_method
    competition rank among reported evaluations in identical conditions, including unlinked observations
    source_file
    5594/leaderboard.json
    source_page
    https://www.kaggle.com/benchmarks/kaggle/dark-hex/versions/1
    measurements
    • name
      Score
      unit
      score
      scale
      1
      metric
      Dark Hex · Score
      result
      resultCase
      numericResult
      booleanResult
      false
      numericResult
      value
      188.04212564387763
      standardDeviation
      0
      confidenceInterval
      0
      hasStandardDeviation
      false
      hasConfidenceInterval
      false
      unevenConfidenceInterval
      plus
      22.895099655371894
      minus
      28.533124695853132
      hasUnevenConfidenceInterval
      true
      taskVersionId
      0
      evaluationDate
      2026-11-11T19:56:36.2751281Z
      hasBooleanResult
      false
      hasNumericResult
      true
      hasTaskVersionId
      false
      hasEvaluationDate
      true
      numericResultNullable
      value
      188.04212564387763
      standardDeviation
      0
      confidenceInterval
      0
      hasStandardDeviation
      false
      hasConfidenceInterval
      false
      unevenConfidenceInterval
      plus
      22.895099655371894
      minus
      28.533124695853132
      hasUnevenConfidenceInterval
      true
      hasNumericResultPublic
      false
      customAdditionalResults
        hasNumericResultPrivate
        false
        task_id
        33066
        sort_order
        DESCENDING
        source_name
        Score
        display_type
        counts
        task_version
        1
        task_display_type
        COUNTS
        normalization_status
        normalized
      published_at
      2026-06-04T13:40:48.173580300Z
      candidate_class
      modelVersion
      methodology_url
      https://www.kaggle.com/game-arena-faq
      source_revision
      b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
      publisher_anchor
      openai/gpt-5-mini-2025-08-07
      game_arena_rating
      Game-specific rating; compare within this game and version
      metric_population
      41
      benchmark_evaluation
      true
      task_metadata_source
      benchmarkVersion
      candidate_metadata_source
      benchmarkVersionMappings
      evaluated at
      2026-11-11T19:56:36.275Z
      source model id
      GPT-5 mini
      confidence lower
      159.5090009480245
      confidence upper
      210.93722529924952
      Original result ↗

      LMArena

      1,152.408

      source id
      lmarena
      leaderboard name
      LMArena Vision Style Control Creative Writing
      dimension
      multimodal
      metric
      Arena rating
      rank
      29
      sample size
      1108
      evaluated at
      2026-01-09T00:00:00.000Z
      source model id
      gpt-5-mini-high
      confidence lower
      1131.597288457494
      confidence upper
      1173.2186769294378
      Original result ↗

      Kaggle Benchmarks

      708.251

      source id
      kaggleBenchmarks
      leaderboard name
      Dots and Boxes · Score
      dimension
      general
      metric
      Dots and Boxes · Score
      rank
      29
      aggregation scope
      kaggle
      true
      status
      published
      license
      Apache-2.0
      direction
      higherIsBetter
      conditions
      task
      id
      36964
      name
      Score
      version
      1
      sort_order
      DESCENDING
      display_type
      counts
      benchmark
      id
      6023
      name
      Dots and Boxes
      type
      GAME
      owner
      kaggle
      version
      1
      categories
        version_id
        6046
        maintainer_tier
        Kaggle-published
        candidate
        candidate_class
        modelVersion
        collection
        kaggleGameArena
        record_kind
        aggregate
        game_arena
        true
        attribution
        Kaggle · kaggle · Dots and Boxes
        license_url
        https://www.apache.org/licenses/LICENSE-2.0
        metric_kind
        Dots and Boxes · Score
        rank_method
        competition rank among reported evaluations in identical conditions, including unlinked observations
        source_file
        6046/leaderboard.json
        source_page
        https://www.kaggle.com/benchmarks/kaggle/dots-and-boxes/versions/1
        measurements
        • name
          Score
          unit
          score
          scale
          1
          metric
          Dots and Boxes · Score
          result
          resultCase
          numericResult
          booleanResult
          false
          numericResult
          value
          708.2514605319411
          standardDeviation
          0
          confidenceInterval
          0
          hasStandardDeviation
          false
          hasConfidenceInterval
          false
          unevenConfidenceInterval
          plus
          28.951506260815904
          minus
          38.6386008673187
          hasUnevenConfidenceInterval
          true
          taskVersionId
          0
          evaluationDate
          2026-11-11T19:59:23.3393358Z
          hasBooleanResult
          false
          hasNumericResult
          true
          hasTaskVersionId
          false
          hasEvaluationDate
          true
          numericResultNullable
          value
          708.2514605319411
          standardDeviation
          0
          confidenceInterval
          0
          hasStandardDeviation
          false
          hasConfidenceInterval
          false
          unevenConfidenceInterval
          plus
          28.951506260815904
          minus
          38.6386008673187
          hasUnevenConfidenceInterval
          true
          hasNumericResultPublic
          false
          customAdditionalResults
            hasNumericResultPrivate
            false
            task_id
            36964
            sort_order
            DESCENDING
            source_name
            Score
            display_type
            counts
            task_version
            1
            task_display_type
            COUNTS
            normalization_status
            normalized
          published_at
          2026-06-17T18:07:42.213532800Z
          candidate_class
          modelVersion
          methodology_url
          https://www.kaggle.com/game-arena-faq
          source_revision
          b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
          publisher_anchor
          openai/gpt-5-mini-2025-08-07
          game_arena_rating
          Game-specific rating; compare within this game and version
          metric_population
          40
          benchmark_evaluation
          true
          task_metadata_source
          benchmarkVersion
          candidate_metadata_source
          benchmarkVersionMappings
          evaluated at
          2026-11-11T19:59:23.339Z
          source model id
          GPT-5 mini
          confidence lower
          669.6128596646224
          confidence upper
          737.202966792757
          Original result ↗

          Kaggle Benchmarks

          682.586

          source id
          kaggleBenchmarks
          leaderboard name
          Checkers · Score
          dimension
          general
          metric
          Checkers · Score
          rank
          30
          aggregation scope
          kaggle
          true
          status
          published
          license
          Apache-2.0
          direction
          higherIsBetter
          conditions
          task
          id
          33515
          name
          Score
          version
          1
          sort_order
          DESCENDING
          display_type
          counts
          benchmark
          id
          5687
          name
          Checkers
          type
          GAME
          owner
          kaggle
          version
          1
          categories
            version_id
            5710
            maintainer_tier
            Kaggle-published
            candidate
            candidate_class
            modelVersion
            collection
            kaggleGameArena
            record_kind
            aggregate
            game_arena
            true
            attribution
            Kaggle · kaggle · Checkers
            license_url
            https://www.apache.org/licenses/LICENSE-2.0
            metric_kind
            Checkers · Score
            rank_method
            competition rank among reported evaluations in identical conditions, including unlinked observations
            source_file
            5710/leaderboard.json
            source_page
            https://www.kaggle.com/benchmarks/kaggle/checkers/versions/1
            measurements
            • name
              Score
              unit
              score
              scale
              1
              metric
              Checkers · Score
              result
              resultCase
              numericResult
              booleanResult
              false
              numericResult
              value
              682.5860292029869
              standardDeviation
              0
              confidenceInterval
              0
              hasStandardDeviation
              false
              hasConfidenceInterval
              false
              unevenConfidenceInterval
              plus
              33.93222137738201
              minus
              34.190532750382886
              hasUnevenConfidenceInterval
              true
              taskVersionId
              0
              evaluationDate
              2026-11-11T19:57:04.5294524Z
              hasBooleanResult
              false
              hasNumericResult
              true
              hasTaskVersionId
              false
              hasEvaluationDate
              true
              numericResultNullable
              value
              682.5860292029869
              standardDeviation
              0
              confidenceInterval
              0
              hasStandardDeviation
              false
              hasConfidenceInterval
              false
              unevenConfidenceInterval
              plus
              33.93222137738201
              minus
              34.190532750382886
              hasUnevenConfidenceInterval
              true
              hasNumericResultPublic
              false
              customAdditionalResults
                hasNumericResultPrivate
                false
                task_id
                33515
                sort_order
                DESCENDING
                source_name
                Score
                display_type
                counts
                task_version
                1
                task_display_type
                COUNTS
                normalization_status
                normalized
              published_at
              2026-06-11T15:24:41.429982100Z
              candidate_class
              modelVersion
              methodology_url
              https://www.kaggle.com/game-arena-faq
              source_revision
              b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
              publisher_anchor
              openai/gpt-5-mini-2025-08-07
              game_arena_rating
              Game-specific rating; compare within this game and version
              metric_population
              41
              benchmark_evaluation
              true
              task_metadata_source
              benchmarkVersion
              candidate_metadata_source
              benchmarkVersionMappings
              evaluated at
              2026-11-11T19:57:04.529Z
              source model id
              GPT-5 mini
              confidence lower
              648.395496452604
              confidence upper
              716.5182505803689
              Original result ↗

              LMArena

              1,226.096

              source id
              lmarena
              leaderboard name
              LMArena Vision Entity Recognition
              dimension
              multimodal
              metric
              Arena rating
              rank
              31
              sample size
              280
              evaluated at
              2026-11-09T00:00:00.000Z
              source model id
              GPT-5 mini (High)
              confidence lower
              1190.117578703092
              confidence upper
              1262.0736017161244
              Original result ↗

              Kaggle Benchmarks

              202.181

              source id
              kaggleBenchmarks
              leaderboard name
              Reversi · Score
              dimension
              general
              metric
              Reversi · Score
              rank
              31
              aggregation scope
              kaggle
              true
              status
              published
              license
              Apache-2.0
              direction
              higherIsBetter
              conditions
              task
              id
              41770
              name
              Score
              version
              1
              sort_order
              DESCENDING
              display_type
              counts
              benchmark
              id
              6489
              name
              Reversi
              type
              GAME
              owner
              kaggle
              version
              1
              categories
                version_id
                6508
                maintainer_tier
                Kaggle-published
                candidate
                candidate_class
                modelVersion
                collection
                kaggleGameArena
                record_kind
                aggregate
                game_arena
                true
                attribution
                Kaggle · kaggle · Reversi
                license_url
                https://www.apache.org/licenses/LICENSE-2.0
                metric_kind
                Reversi · Score
                rank_method
                competition rank among reported evaluations in identical conditions, including unlinked observations
                source_file
                6508/leaderboard.json
                source_page
                https://www.kaggle.com/benchmarks/kaggle/reversi/versions/1
                measurements
                • name
                  Score
                  unit
                  score
                  scale
                  1
                  metric
                  Reversi · Score
                  result
                  resultCase
                  numericResult
                  booleanResult
                  false
                  numericResult
                  value
                  202.18084428517636
                  standardDeviation
                  0
                  confidenceInterval
                  0
                  hasStandardDeviation
                  false
                  hasConfidenceInterval
                  false
                  unevenConfidenceInterval
                  plus
                  46.62361461918502
                  minus
                  73.32903315661252
                  hasUnevenConfidenceInterval
                  true
                  taskVersionId
                  0
                  evaluationDate
                  2026-11-11T20:01:44.8028176Z
                  hasBooleanResult
                  false
                  hasNumericResult
                  true
                  hasTaskVersionId
                  false
                  hasEvaluationDate
                  true
                  numericResultNullable
                  value
                  202.18084428517636
                  standardDeviation
                  0
                  confidenceInterval
                  0
                  hasStandardDeviation
                  false
                  hasConfidenceInterval
                  false
                  unevenConfidenceInterval
                  plus
                  46.62361461918502
                  minus
                  73.32903315661252
                  hasUnevenConfidenceInterval
                  true
                  hasNumericResultPublic
                  false
                  customAdditionalResults
                    hasNumericResultPrivate
                    false
                    task_id
                    41770
                    sort_order
                    DESCENDING
                    source_name
                    Score
                    display_type
                    counts
                    task_version
                    1
                    task_display_type
                    COUNTS
                    normalization_status
                    normalized
                  published_at
                  2026-08-11T18:29:54.894504100Z
                  candidate_class
                  modelVersion
                  methodology_url
                  https://www.kaggle.com/game-arena-faq
                  source_revision
                  b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                  publisher_anchor
                  openai/gpt-5-mini-2025-08-07
                  game_arena_rating
                  Game-specific rating; compare within this game and version
                  metric_population
                  39
                  benchmark_evaluation
                  true
                  task_metadata_source
                  benchmarkVersion
                  candidate_metadata_source
                  benchmarkVersionMappings
                  evaluated at
                  2026-11-11T20:01:44.802Z
                  source model id
                  GPT-5 mini
                  confidence lower
                  128.85181112856384
                  confidence upper
                  248.80445890436138
                  Original result ↗

                  Kaggle Benchmarks

                  142.53

                  source id
                  kaggleBenchmarks
                  leaderboard name
                  Bargaining · Score
                  dimension
                  general
                  metric
                  Bargaining · Score
                  rank
                  31
                  aggregation scope
                  kaggle
                  true
                  status
                  published
                  license
                  Apache-2.0
                  direction
                  higherIsBetter
                  conditions
                  task
                  id
                  37611
                  name
                  Score
                  version
                  1
                  sort_order
                  DESCENDING
                  display_type
                  counts
                  benchmark
                  id
                  6128
                  name
                  Bargaining
                  type
                  GAME
                  owner
                  kaggle
                  version
                  1
                  categories
                    version_id
                    6152
                    maintainer_tier
                    Kaggle-published
                    candidate
                    candidate_class
                    modelVersion
                    collection
                    kaggleGameArena
                    record_kind
                    aggregate
                    game_arena
                    true
                    attribution
                    Kaggle · kaggle · Bargaining
                    license_url
                    https://www.apache.org/licenses/LICENSE-2.0
                    metric_kind
                    Bargaining · Score
                    rank_method
                    competition rank among reported evaluations in identical conditions, including unlinked observations
                    source_file
                    6152/leaderboard.json
                    source_page
                    https://www.kaggle.com/benchmarks/kaggle/bargaining/versions/1
                    measurements
                    • name
                      Score
                      unit
                      score
                      scale
                      1
                      metric
                      Bargaining · Score
                      result
                      resultCase
                      numericResult
                      booleanResult
                      false
                      numericResult
                      value
                      142.5296321446333
                      standardDeviation
                      0
                      confidenceInterval
                      0
                      hasStandardDeviation
                      false
                      hasConfidenceInterval
                      false
                      unevenConfidenceInterval
                      plus
                      12.936109058264122
                      minus
                      14.671781085086792
                      hasUnevenConfidenceInterval
                      true
                      taskVersionId
                      0
                      evaluationDate
                      2026-11-11T20:00:44.5076442Z
                      hasBooleanResult
                      false
                      hasNumericResult
                      true
                      hasTaskVersionId
                      false
                      hasEvaluationDate
                      true
                      numericResultNullable
                      value
                      142.5296321446333
                      standardDeviation
                      0
                      confidenceInterval
                      0
                      hasStandardDeviation
                      false
                      hasConfidenceInterval
                      false
                      unevenConfidenceInterval
                      plus
                      12.936109058264122
                      minus
                      14.671781085086792
                      hasUnevenConfidenceInterval
                      true
                      hasNumericResultPublic
                      false
                      customAdditionalResults
                        hasNumericResultPrivate
                        false
                        task_id
                        37611
                        sort_order
                        DESCENDING
                        source_name
                        Score
                        display_type
                        counts
                        task_version
                        1
                        task_display_type
                        COUNTS
                        normalization_status
                        normalized
                      published_at
                      2026-07-23T16:10:38.700299600Z
                      candidate_class
                      modelVersion
                      methodology_url
                      https://www.kaggle.com/game-arena-faq
                      source_revision
                      b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                      publisher_anchor
                      openai/gpt-5-mini-2025-08-07
                      game_arena_rating
                      Game-specific rating; compare within this game and version
                      metric_population
                      39
                      benchmark_evaluation
                      true
                      task_metadata_source
                      benchmarkVersion
                      candidate_metadata_source
                      benchmarkVersionMappings
                      evaluated at
                      2026-11-11T20:00:44.507Z
                      source model id
                      GPT-5 mini
                      confidence lower
                      127.8578510595465
                      confidence upper
                      155.46574120289742
                      Original result ↗

                      Kaggle Benchmarks

                      -49.68

                      source id
                      kaggleBenchmarks
                      leaderboard name
                      Heads Up Poker · Mean BB/100
                      dimension
                      general
                      metric
                      Heads Up Poker · Mean BB/100
                      rank
                      31
                      aggregation scope
                      kaggle
                      true
                      status
                      published
                      license
                      Apache-2.0
                      direction
                      higherIsBetter
                      conditions
                      task
                      id
                      775
                      name
                      Mean BB/100
                      version
                      1
                      sort_order
                      DESCENDING
                      display_type
                      counts
                      benchmark
                      id
                      201
                      name
                      Heads Up Poker
                      type
                      GAME
                      owner
                      kaggle
                      version
                      1
                      categories
                        version_id
                        180
                        maintainer_tier
                        Kaggle-published
                        candidate
                        candidate_class
                        modelVersion
                        collection
                        kaggleGameArena
                        record_kind
                        aggregate
                        game_arena
                        true
                        attribution
                        Kaggle · kaggle · Heads Up Poker
                        license_url
                        https://www.apache.org/licenses/LICENSE-2.0
                        metric_kind
                        Heads Up Poker · Mean BB/100
                        rank_method
                        competition rank among reported evaluations in identical conditions, including unlinked observations
                        source_file
                        180/leaderboard.json
                        source_page
                        https://www.kaggle.com/benchmarks/kaggle/poker-heads-up/versions/1
                        measurements
                        • name
                          Mean BB/100
                          unit
                          score
                          scale
                          1
                          metric
                          Heads Up Poker · Mean BB/100
                          result
                          resultCase
                          numericResult
                          booleanResult
                          false
                          numericResult
                          value
                          -49.680068681318645
                          standardDeviation
                          0
                          confidenceInterval
                          0
                          hasStandardDeviation
                          false
                          hasConfidenceInterval
                          false
                          unevenConfidenceInterval
                          plus
                          4.646369047619011
                          minus
                          5.010632631257671
                          hasUnevenConfidenceInterval
                          true
                          taskVersionId
                          0
                          evaluationDate
                          2026-10-08T17:19:02.7626688Z
                          hasBooleanResult
                          false
                          hasNumericResult
                          true
                          hasTaskVersionId
                          false
                          hasEvaluationDate
                          true
                          numericResultNullable
                          value
                          -49.680068681318645
                          standardDeviation
                          0
                          confidenceInterval
                          0
                          hasStandardDeviation
                          false
                          hasConfidenceInterval
                          false
                          unevenConfidenceInterval
                          plus
                          4.646369047619011
                          minus
                          5.010632631257671
                          hasUnevenConfidenceInterval
                          true
                          hasNumericResultPublic
                          false
                          customAdditionalResults
                            hasNumericResultPrivate
                            false
                            task_id
                            775
                            sort_order
                            DESCENDING
                            source_name
                            Mean BB/100
                            display_type
                            counts
                            task_version
                            1
                            task_display_type
                            COUNTS
                            normalization_status
                            normalized
                          published_at
                          2026-02-02T15:50:27.731526100Z
                          candidate_class
                          modelVersion
                          methodology_url
                          https://www.kaggle.com/game-arena-faq
                          source_revision
                          b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                          publisher_anchor
                          openai/gpt-5-mini-2025-08-07
                          game_arena_rating
                          Game-specific rating; compare within this game and version
                          metric_population
                          31
                          benchmark_evaluation
                          true
                          task_metadata_source
                          benchmarkVersion
                          candidate_metadata_source
                          benchmarkVersionMappings
                          evaluated at
                          2026-10-08T17:19:02.762Z
                          source model id
                          GPT-5 mini
                          confidence lower
                          -54.690701312576316
                          confidence upper
                          -45.033699633699634
                          Original result ↗

                          Kaggle Benchmarks

                          82.563

                          source id
                          kaggleBenchmarks
                          leaderboard name
                          Word Association · Score
                          dimension
                          general
                          metric
                          Word Association · Score
                          rank
                          32
                          aggregation scope
                          kaggle
                          true
                          status
                          published
                          license
                          Apache-2.0
                          direction
                          higherIsBetter
                          conditions
                          task
                          id
                          27256
                          name
                          Score
                          version
                          1
                          sort_order
                          DESCENDING
                          display_type
                          counts
                          benchmark
                          id
                          4537
                          name
                          Word Association
                          type
                          GAME
                          owner
                          kaggle
                          version
                          1
                          categories
                            version_id
                            4560
                            maintainer_tier
                            Kaggle-published
                            candidate
                            candidate_class
                            modelVersion
                            collection
                            kaggleGameArena
                            record_kind
                            aggregate
                            game_arena
                            true
                            attribution
                            Kaggle · kaggle · Word Association
                            license_url
                            https://www.apache.org/licenses/LICENSE-2.0
                            metric_kind
                            Word Association · Score
                            rank_method
                            competition rank among reported evaluations in identical conditions, including unlinked observations
                            source_file
                            4560/leaderboard.json
                            source_page
                            https://www.kaggle.com/benchmarks/kaggle/word-association/versions/1
                            measurements
                            • name
                              Score
                              unit
                              score
                              scale
                              1
                              metric
                              Word Association · Score
                              result
                              resultCase
                              numericResult
                              booleanResult
                              false
                              numericResult
                              value
                              82.56342769678042
                              standardDeviation
                              0
                              confidenceInterval
                              0
                              hasStandardDeviation
                              false
                              hasConfidenceInterval
                              false
                              unevenConfidenceInterval
                              plus
                              34.751058689425605
                              minus
                              43.40425469953662
                              hasUnevenConfidenceInterval
                              true
                              taskVersionId
                              0
                              evaluationDate
                              2026-11-11T19:58:55.7420417Z
                              hasBooleanResult
                              false
                              hasNumericResult
                              true
                              hasTaskVersionId
                              false
                              hasEvaluationDate
                              true
                              numericResultNullable
                              value
                              82.56342769678042
                              standardDeviation
                              0
                              confidenceInterval
                              0
                              hasStandardDeviation
                              false
                              hasConfidenceInterval
                              false
                              unevenConfidenceInterval
                              plus
                              34.751058689425605
                              minus
                              43.40425469953662
                              hasUnevenConfidenceInterval
                              true
                              hasNumericResultPublic
                              false
                              customAdditionalResults
                                hasNumericResultPrivate
                                false
                                task_id
                                27256
                                sort_order
                                DESCENDING
                                source_name
                                Score
                                display_type
                                counts
                                task_version
                                1
                                task_display_type
                                COUNTS
                                normalization_status
                                normalized
                              published_at
                              2026-05-26T19:37:29.256086900Z
                              candidate_class
                              modelVersion
                              methodology_url
                              https://www.kaggle.com/game-arena-faq
                              source_revision
                              b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                              publisher_anchor
                              openai/gpt-5-mini-2025-08-07
                              game_arena_rating
                              Game-specific rating; compare within this game and version
                              metric_population
                              40
                              benchmark_evaluation
                              true
                              task_metadata_source
                              benchmarkVersion
                              candidate_metadata_source
                              benchmarkVersionMappings
                              evaluated at
                              2026-11-11T19:58:55.742Z
                              source model id
                              GPT-5 mini
                              confidence lower
                              39.1591729972438
                              confidence upper
                              117.31448638620603
                              Original result ↗

                              Kaggle Benchmarks

                              227.788

                              source id
                              kaggleBenchmarks
                              leaderboard name
                              Coin Game · Score
                              dimension
                              general
                              metric
                              Coin Game · Score
                              rank
                              33
                              aggregation scope
                              kaggle
                              true
                              status
                              published
                              license
                              Apache-2.0
                              direction
                              higherIsBetter
                              conditions
                              task
                              id
                              34561
                              name
                              Score
                              version
                              1
                              sort_order
                              DESCENDING
                              display_type
                              counts
                              benchmark
                              id
                              5821
                              name
                              Coin Game
                              type
                              GAME
                              owner
                              kaggle
                              version
                              1
                              categories
                                version_id
                                5844
                                maintainer_tier
                                Kaggle-published
                                candidate
                                candidate_class
                                modelVersion
                                collection
                                kaggleGameArena
                                record_kind
                                aggregate
                                game_arena
                                true
                                attribution
                                Kaggle · kaggle · Coin Game
                                license_url
                                https://www.apache.org/licenses/LICENSE-2.0
                                metric_kind
                                Coin Game · Score
                                rank_method
                                competition rank among reported evaluations in identical conditions, including unlinked observations
                                source_file
                                5844/leaderboard.json
                                source_page
                                https://www.kaggle.com/benchmarks/kaggle/coin-game/versions/1
                                measurements
                                • name
                                  Score
                                  unit
                                  score
                                  scale
                                  1
                                  metric
                                  Coin Game · Score
                                  result
                                  resultCase
                                  numericResult
                                  booleanResult
                                  false
                                  numericResult
                                  value
                                  227.78763274018763
                                  standardDeviation
                                  0
                                  confidenceInterval
                                  0
                                  hasStandardDeviation
                                  false
                                  hasConfidenceInterval
                                  false
                                  unevenConfidenceInterval
                                  plus
                                  24.832231341108013
                                  minus
                                  27.870832840481967
                                  hasUnevenConfidenceInterval
                                  true
                                  taskVersionId
                                  0
                                  evaluationDate
                                  2026-11-11T19:58:27.1740754Z
                                  hasBooleanResult
                                  false
                                  hasNumericResult
                                  true
                                  hasTaskVersionId
                                  false
                                  hasEvaluationDate
                                  true
                                  numericResultNullable
                                  value
                                  227.78763274018763
                                  standardDeviation
                                  0
                                  confidenceInterval
                                  0
                                  hasStandardDeviation
                                  false
                                  hasConfidenceInterval
                                  false
                                  unevenConfidenceInterval
                                  plus
                                  24.832231341108013
                                  minus
                                  27.870832840481967
                                  hasUnevenConfidenceInterval
                                  true
                                  hasNumericResultPublic
                                  false
                                  customAdditionalResults
                                    hasNumericResultPrivate
                                    false
                                    task_id
                                    34561
                                    sort_order
                                    DESCENDING
                                    source_name
                                    Score
                                    display_type
                                    counts
                                    task_version
                                    1
                                    task_display_type
                                    COUNTS
                                    normalization_status
                                    normalized
                                  published_at
                                  2026-07-08T17:58:41.243600500Z
                                  candidate_class
                                  modelVersion
                                  methodology_url
                                  https://www.kaggle.com/game-arena-faq
                                  source_revision
                                  b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                  publisher_anchor
                                  openai/gpt-5-mini-2025-08-07
                                  game_arena_rating
                                  Game-specific rating; compare within this game and version
                                  metric_population
                                  39
                                  benchmark_evaluation
                                  true
                                  task_metadata_source
                                  benchmarkVersion
                                  candidate_metadata_source
                                  benchmarkVersionMappings
                                  evaluated at
                                  2026-11-11T19:58:27.174Z
                                  source model id
                                  GPT-5 mini
                                  confidence lower
                                  199.91679989970567
                                  confidence upper
                                  252.61986408129565
                                  Original result ↗

                                  OpenRouter Benchmarks

                                  80.682%

                                  source id
                                  openRouterBenchmarks
                                  leaderboard name
                                  GPQA Diamond · Accuracy · Azure
                                  dimension
                                  knowledge
                                  metric
                                  GPQA Diamond · Accuracy
                                  rank
                                  33
                                  sample size
                                  792
                                  aggregation scope
                                  status
                                  published
                                  harness
                                  url
                                  https://github.com/OpenRouterTeam/benchmark-harness
                                  name
                                  OpenRouter benchmark harness
                                  direction
                                  higherIsBetter
                                  run_count
                                  4
                                  conditions
                                  window
                                  newest 90 days; successful visible nonzero runs
                                  dataset
                                  benchmark-leaderboard
                                  benchmark
                                  id
                                  gpqa_diamond
                                  name
                                  GPQA Diamond
                                  record_kind
                                  aggregate
                                  provider_name
                                  Azure
                                  attribution
                                  Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
                                  last_run_at
                                  2026-10-01T19:34:33.810Z
                                  license_url
                                  https://creativecommons.org/licenses/by/4.0/
                                  methodology
                                  Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
                                  metric_kind
                                  GPQA Diamond · Accuracy
                                  rank_method
                                  competition rank among reported evaluations in identical conditions, including unlinked observations
                                  sample_size
                                  792
                                  source_file
                                  benchmark-leaderboard.json
                                  source_page
                                  https://openrouter.ai/benchmarks/gpqa-diamond
                                  measurements
                                  accuracy
                                  0.8068179999999999
                                  accuracy_std_dev
                                  0.027363478050131
                                  cost_per_task_usd
                                  0.046258910353535354
                                  output_tokens_per_task
                                  21946.10606060606
                                  latency_seconds_per_task
                                  196.12559974747475
                                  published_at
                                  2026-11-16T01:46:02.653Z
                                  snapshot_date
                                  2026-11-16
                                  source_revision
                                  7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
                                  transformations
                                  TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
                                  metric_population
                                  43
                                  benchmark_evaluation
                                  true
                                  openrouter_permaslug
                                  openai/gpt-5-mini-2025-08-07
                                  source model id
                                  openai/gpt-5-mini-2025-08-07
                                  Original result ↗

                                  Kaggle Benchmarks

                                  291.671

                                  source id
                                  kaggleBenchmarks
                                  leaderboard name
                                  Nine Men's Morris · Score
                                  dimension
                                  general
                                  metric
                                  Nine Men's Morris · Score
                                  rank
                                  34
                                  aggregation scope
                                  kaggle
                                  true
                                  status
                                  published
                                  license
                                  Apache-2.0
                                  direction
                                  higherIsBetter
                                  conditions
                                  task
                                  id
                                  41675
                                  name
                                  Score
                                  version
                                  1
                                  sort_order
                                  DESCENDING
                                  display_type
                                  counts
                                  benchmark
                                  id
                                  6479
                                  name
                                  Nine Men's Morris
                                  type
                                  GAME
                                  owner
                                  kaggle
                                  version
                                  1
                                  categories
                                    version_id
                                    6498
                                    maintainer_tier
                                    Kaggle-published
                                    candidate
                                    candidate_class
                                    modelVersion
                                    collection
                                    kaggleGameArena
                                    record_kind
                                    aggregate
                                    game_arena
                                    true
                                    attribution
                                    Kaggle · kaggle · Nine Men's Morris
                                    license_url
                                    https://www.apache.org/licenses/LICENSE-2.0
                                    metric_kind
                                    Nine Men's Morris · Score
                                    rank_method
                                    competition rank among reported evaluations in identical conditions, including unlinked observations
                                    source_file
                                    6498/leaderboard.json
                                    source_page
                                    https://www.kaggle.com/benchmarks/kaggle/nine-mens-morris/versions/1
                                    measurements
                                    • name
                                      Score
                                      unit
                                      score
                                      scale
                                      1
                                      metric
                                      Nine Men's Morris · Score
                                      result
                                      resultCase
                                      numericResult
                                      booleanResult
                                      false
                                      numericResult
                                      value
                                      291.6706269702006
                                      standardDeviation
                                      0
                                      confidenceInterval
                                      0
                                      hasStandardDeviation
                                      false
                                      hasConfidenceInterval
                                      false
                                      unevenConfidenceInterval
                                      plus
                                      47.651671854726374
                                      minus
                                      50.716175090876334
                                      hasUnevenConfidenceInterval
                                      true
                                      taskVersionId
                                      0
                                      evaluationDate
                                      2026-11-11T20:01:17.6916056Z
                                      hasBooleanResult
                                      false
                                      hasNumericResult
                                      true
                                      hasTaskVersionId
                                      false
                                      hasEvaluationDate
                                      true
                                      numericResultNullable
                                      value
                                      291.6706269702006
                                      standardDeviation
                                      0
                                      confidenceInterval
                                      0
                                      hasStandardDeviation
                                      false
                                      hasConfidenceInterval
                                      false
                                      unevenConfidenceInterval
                                      plus
                                      47.651671854726374
                                      minus
                                      50.716175090876334
                                      hasUnevenConfidenceInterval
                                      true
                                      hasNumericResultPublic
                                      false
                                      customAdditionalResults
                                        hasNumericResultPrivate
                                        false
                                        task_id
                                        41675
                                        sort_order
                                        DESCENDING
                                        source_name
                                        Score
                                        display_type
                                        counts
                                        task_version
                                        1
                                        task_display_type
                                        COUNTS
                                        normalization_status
                                        normalized
                                      published_at
                                      2026-08-04T20:43:32.035505100Z
                                      candidate_class
                                      modelVersion
                                      methodology_url
                                      https://www.kaggle.com/game-arena-faq
                                      source_revision
                                      b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                      publisher_anchor
                                      openai/gpt-5-mini-2025-08-07
                                      game_arena_rating
                                      Game-specific rating; compare within this game and version
                                      metric_population
                                      39
                                      benchmark_evaluation
                                      true
                                      task_metadata_source
                                      benchmarkVersion
                                      candidate_metadata_source
                                      benchmarkVersionMappings
                                      evaluated at
                                      2026-11-11T20:01:17.691Z
                                      source model id
                                      GPT-5 mini
                                      confidence lower
                                      240.95445187932427
                                      confidence upper
                                      339.322298824927
                                      Original result ↗

                                      Kaggle Benchmarks

                                      538.583

                                      source id
                                      kaggleBenchmarks
                                      leaderboard name
                                      Chess · Score
                                      dimension
                                      general
                                      metric
                                      Chess · Score
                                      rank
                                      35
                                      aggregation scope
                                      kaggle
                                      true
                                      status
                                      published
                                      license
                                      Apache-2.0
                                      direction
                                      higherIsBetter
                                      conditions
                                      task
                                      id
                                      1446
                                      name
                                      Score
                                      version
                                      1
                                      sort_order
                                      DESCENDING
                                      display_type
                                      counts
                                      benchmark
                                      id
                                      147
                                      name
                                      Chess
                                      type
                                      GAME
                                      owner
                                      kaggle
                                      version
                                      2
                                      categories
                                        version_id
                                        349
                                        maintainer_tier
                                        Kaggle-published
                                        candidate
                                        candidate_class
                                        modelVersion
                                        collection
                                        kaggleGameArena
                                        record_kind
                                        aggregate
                                        game_arena
                                        true
                                        attribution
                                        Kaggle · kaggle · Chess
                                        license_url
                                        https://www.apache.org/licenses/LICENSE-2.0
                                        metric_kind
                                        Chess · Score
                                        rank_method
                                        competition rank among reported evaluations in identical conditions, including unlinked observations
                                        source_file
                                        349/leaderboard.json
                                        source_page
                                        https://www.kaggle.com/benchmarks/kaggle/chess-text/versions/2
                                        measurements
                                        • name
                                          Score
                                          unit
                                          score
                                          scale
                                          1
                                          metric
                                          Chess · Score
                                          result
                                          resultCase
                                          numericResult
                                          booleanResult
                                          false
                                          numericResult
                                          value
                                          538.5827064346333
                                          standardDeviation
                                          0
                                          confidenceInterval
                                          0
                                          hasStandardDeviation
                                          false
                                          hasConfidenceInterval
                                          false
                                          unevenConfidenceInterval
                                          plus
                                          43.13619464476801
                                          minus
                                          56.4977525774118
                                          hasUnevenConfidenceInterval
                                          true
                                          taskVersionId
                                          0
                                          evaluationDate
                                          2026-11-11T20:03:32.6840746Z
                                          hasBooleanResult
                                          false
                                          hasNumericResult
                                          true
                                          hasTaskVersionId
                                          false
                                          hasEvaluationDate
                                          true
                                          numericResultNullable
                                          value
                                          538.5827064346333
                                          standardDeviation
                                          0
                                          confidenceInterval
                                          0
                                          hasStandardDeviation
                                          false
                                          hasConfidenceInterval
                                          false
                                          unevenConfidenceInterval
                                          plus
                                          43.13619464476801
                                          minus
                                          56.4977525774118
                                          hasUnevenConfidenceInterval
                                          true
                                          hasNumericResultPublic
                                          false
                                          customAdditionalResults
                                            hasNumericResultPrivate
                                            false
                                            task_id
                                            1446
                                            sort_order
                                            DESCENDING
                                            source_name
                                            Score
                                            display_type
                                            counts
                                            task_version
                                            1
                                            task_display_type
                                            COUNTS
                                            normalization_status
                                            normalized
                                          published_at
                                          2026-02-02T15:46:19.333333900Z
                                          candidate_class
                                          modelVersion
                                          methodology_url
                                          https://www.kaggle.com/game-arena-faq
                                          source_revision
                                          b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                          publisher_anchor
                                          openai/gpt-5-mini-2025-08-07
                                          game_arena_rating
                                          Game-specific rating; compare within this game and version
                                          metric_population
                                          42
                                          benchmark_evaluation
                                          true
                                          task_metadata_source
                                          benchmarkVersion
                                          candidate_metadata_source
                                          benchmarkVersionMappings
                                          evaluated at
                                          2026-11-11T20:03:32.684Z
                                          source model id
                                          GPT-5 mini
                                          confidence lower
                                          482.08495385722154
                                          confidence upper
                                          581.7189010794013
                                          Original result ↗

                                          Kaggle Benchmarks

                                          43.449

                                          source id
                                          kaggleBenchmarks
                                          leaderboard name
                                          Clobber · Score
                                          dimension
                                          general
                                          metric
                                          Clobber · Score
                                          rank
                                          35
                                          aggregation scope
                                          kaggle
                                          true
                                          status
                                          published
                                          license
                                          Apache-2.0
                                          direction
                                          higherIsBetter
                                          conditions
                                          task
                                          id
                                          34472
                                          name
                                          Score
                                          version
                                          1
                                          sort_order
                                          DESCENDING
                                          display_type
                                          counts
                                          benchmark
                                          id
                                          5816
                                          name
                                          Clobber
                                          type
                                          GAME
                                          owner
                                          kaggle
                                          version
                                          1
                                          categories
                                            version_id
                                            5839
                                            maintainer_tier
                                            Kaggle-published
                                            candidate
                                            candidate_class
                                            modelVersion
                                            collection
                                            kaggleGameArena
                                            record_kind
                                            aggregate
                                            game_arena
                                            true
                                            attribution
                                            Kaggle · kaggle · Clobber
                                            license_url
                                            https://www.apache.org/licenses/LICENSE-2.0
                                            metric_kind
                                            Clobber · Score
                                            rank_method
                                            competition rank among reported evaluations in identical conditions, including unlinked observations
                                            source_file
                                            5839/leaderboard.json
                                            source_page
                                            https://www.kaggle.com/benchmarks/kaggle/clobber/versions/1
                                            measurements
                                            • name
                                              Score
                                              unit
                                              score
                                              scale
                                              1
                                              metric
                                              Clobber · Score
                                              result
                                              resultCase
                                              numericResult
                                              booleanResult
                                              false
                                              numericResult
                                              value
                                              43.44920143575223
                                              standardDeviation
                                              0
                                              confidenceInterval
                                              0
                                              hasStandardDeviation
                                              false
                                              hasConfidenceInterval
                                              false
                                              unevenConfidenceInterval
                                              plus
                                              42.1132220586106
                                              minus
                                              44.109813369093885
                                              hasUnevenConfidenceInterval
                                              true
                                              taskVersionId
                                              0
                                              evaluationDate
                                              2026-11-11T19:57:33.0562958Z
                                              hasBooleanResult
                                              false
                                              hasNumericResult
                                              true
                                              hasTaskVersionId
                                              false
                                              hasEvaluationDate
                                              true
                                              numericResultNullable
                                              value
                                              43.44920143575223
                                              standardDeviation
                                              0
                                              confidenceInterval
                                              0
                                              hasStandardDeviation
                                              false
                                              hasConfidenceInterval
                                              false
                                              unevenConfidenceInterval
                                              plus
                                              42.1132220586106
                                              minus
                                              44.109813369093885
                                              hasUnevenConfidenceInterval
                                              true
                                              hasNumericResultPublic
                                              false
                                              customAdditionalResults
                                                hasNumericResultPrivate
                                                false
                                                task_id
                                                34472
                                                sort_order
                                                DESCENDING
                                                source_name
                                                Score
                                                display_type
                                                counts
                                                task_version
                                                1
                                                task_display_type
                                                COUNTS
                                                normalization_status
                                                normalized
                                              published_at
                                              2026-06-25T16:16:58.883878300Z
                                              candidate_class
                                              modelVersion
                                              methodology_url
                                              https://www.kaggle.com/game-arena-faq
                                              source_revision
                                              b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                              publisher_anchor
                                              openai/gpt-5-mini-2025-08-07
                                              game_arena_rating
                                              Game-specific rating; compare within this game and version
                                              metric_population
                                              39
                                              benchmark_evaluation
                                              true
                                              task_metadata_source
                                              benchmarkVersion
                                              candidate_metadata_source
                                              benchmarkVersionMappings
                                              evaluated at
                                              2026-11-11T19:57:33.056Z
                                              source model id
                                              GPT-5 mini
                                              confidence lower
                                              -0.6606119333416558
                                              confidence upper
                                              85.56242349436283
                                              Original result ↗

                                              Kaggle Benchmarks

                                              137.522

                                              source id
                                              kaggleBenchmarks
                                              leaderboard name
                                              Lines of Action · Score
                                              dimension
                                              general
                                              metric
                                              Lines of Action · Score
                                              rank
                                              37
                                              aggregation scope
                                              kaggle
                                              true
                                              status
                                              published
                                              license
                                              Apache-2.0
                                              direction
                                              higherIsBetter
                                              conditions
                                              task
                                              id
                                              34467
                                              name
                                              Score
                                              version
                                              1
                                              sort_order
                                              DESCENDING
                                              display_type
                                              counts
                                              benchmark
                                              id
                                              5814
                                              name
                                              Lines of Action
                                              type
                                              GAME
                                              owner
                                              kaggle
                                              version
                                              1
                                              categories
                                                version_id
                                                5837
                                                maintainer_tier
                                                Kaggle-published
                                                candidate
                                                candidate_class
                                                modelVersion
                                                collection
                                                kaggleGameArena
                                                record_kind
                                                aggregate
                                                game_arena
                                                true
                                                attribution
                                                Kaggle · kaggle · Lines of Action
                                                license_url
                                                https://www.apache.org/licenses/LICENSE-2.0
                                                metric_kind
                                                Lines of Action · Score
                                                rank_method
                                                competition rank among reported evaluations in identical conditions, including unlinked observations
                                                source_file
                                                5837/leaderboard.json
                                                source_page
                                                https://www.kaggle.com/benchmarks/kaggle/lines-of-action/versions/1
                                                measurements
                                                • name
                                                  Score
                                                  unit
                                                  score
                                                  scale
                                                  1
                                                  metric
                                                  Lines of Action · Score
                                                  result
                                                  resultCase
                                                  numericResult
                                                  booleanResult
                                                  false
                                                  numericResult
                                                  value
                                                  137.5223682893211
                                                  standardDeviation
                                                  0
                                                  confidenceInterval
                                                  0
                                                  hasStandardDeviation
                                                  false
                                                  hasConfidenceInterval
                                                  false
                                                  unevenConfidenceInterval
                                                  plus
                                                  49.44186671191176
                                                  minus
                                                  72.65336403855686
                                                  hasUnevenConfidenceInterval
                                                  true
                                                  taskVersionId
                                                  0
                                                  evaluationDate
                                                  2026-11-11T19:57:59.1350406Z
                                                  hasBooleanResult
                                                  false
                                                  hasNumericResult
                                                  true
                                                  hasTaskVersionId
                                                  false
                                                  hasEvaluationDate
                                                  true
                                                  numericResultNullable
                                                  value
                                                  137.5223682893211
                                                  standardDeviation
                                                  0
                                                  confidenceInterval
                                                  0
                                                  hasStandardDeviation
                                                  false
                                                  hasConfidenceInterval
                                                  false
                                                  unevenConfidenceInterval
                                                  plus
                                                  49.44186671191176
                                                  minus
                                                  72.65336403855686
                                                  hasUnevenConfidenceInterval
                                                  true
                                                  hasNumericResultPublic
                                                  false
                                                  customAdditionalResults
                                                    hasNumericResultPrivate
                                                    false
                                                    task_id
                                                    34467
                                                    sort_order
                                                    DESCENDING
                                                    source_name
                                                    Score
                                                    display_type
                                                    counts
                                                    task_version
                                                    1
                                                    task_display_type
                                                    COUNTS
                                                    normalization_status
                                                    normalized
                                                  published_at
                                                  2026-07-16T23:03:18.619026400Z
                                                  candidate_class
                                                  modelVersion
                                                  methodology_url
                                                  https://www.kaggle.com/game-arena-faq
                                                  source_revision
                                                  b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
                                                  publisher_anchor
                                                  openai/gpt-5-mini-2025-08-07
                                                  game_arena_rating
                                                  Game-specific rating; compare within this game and version
                                                  metric_population
                                                  39
                                                  benchmark_evaluation
                                                  true
                                                  task_metadata_source
                                                  benchmarkVersion
                                                  candidate_metadata_source
                                                  benchmarkVersionMappings
                                                  evaluated at
                                                  2026-11-11T19:57:59.135Z
                                                  source model id
                                                  GPT-5 mini
                                                  confidence lower
                                                  64.86900425076423
                                                  confidence upper
                                                  186.96423500123285
                                                  Original result ↗

                                                  Published prices

                                                  1–20 / 42

                                                  gpt-5-mini ↗

                                                  $0.02

                                                  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-5-mini ↗

                                                  $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-5-mini ↗

                                                  $0.16

                                                  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-5-mini ↗

                                                  $1.30

                                                  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-5-mini ↗

                                                  $0.03

                                                  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-5-mini ↗

                                                  $0.25

                                                  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-5-mini ↗

                                                  $2.00

                                                  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-5-mini ↗

                                                  $0.02

                                                  Inference provider
                                                  openRouter
                                                  Platform
                                                  OpenRouter
                                                  Unit
                                                  cache_read_tokens_per_million
                                                  Currency
                                                  USD
                                                  Billing conditions

                                                  openai/gpt-5-mini ↗

                                                  $0.25

                                                  Inference provider
                                                  openRouter
                                                  Platform
                                                  OpenRouter
                                                  Unit
                                                  input_tokens_per_million
                                                  Currency
                                                  USD
                                                  Billing conditions

                                                  openai/gpt-5-mini ↗

                                                  $2.00

                                                  Inference provider
                                                  openRouter
                                                  Platform
                                                  OpenRouter
                                                  Unit
                                                  output_tokens_per_million
                                                  Currency
                                                  USD
                                                  Billing conditions

                                                  openai/gpt-5-mini ↗

                                                  $0.01

                                                  Inference provider
                                                  openRouter
                                                  Platform
                                                  OpenRouter
                                                  Unit
                                                  web_search
                                                  Currency
                                                  USD
                                                  Billing conditions

                                                  openai/gpt-5-mini:batch ↗

                                                  $0.01

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

                                                  openai/gpt-5-mini:batch ↗

                                                  $0.13

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

                                                  openai/gpt-5-mini:batch ↗

                                                  $1.00

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

                                                  openai/gpt-5-mini ↗

                                                  $0.03

                                                  Inference provider
                                                  vercelAIGatewayCatalog
                                                  Platform
                                                  azure
                                                  Unit
                                                  cache_read_tokens_per_million
                                                  Currency
                                                  USD
                                                  Billing conditions
                                                  endpoint
                                                  azure | openai/gpt-5-mini
                                                  model_type
                                                  language
                                                  billing_scope
                                                  via Vercel AI Gateway
                                                  Billing label
                                                  Cached input / 1M
                                                  Pricing via
                                                  Vercel AI Gateway

                                                  openai/gpt-5-mini ↗

                                                  $0.25

                                                  Inference provider
                                                  vercelAIGatewayCatalog
                                                  Platform
                                                  azure
                                                  Unit
                                                  input_tokens_per_million
                                                  Currency
                                                  USD
                                                  Billing conditions
                                                  endpoint
                                                  azure | openai/gpt-5-mini
                                                  model_type
                                                  language
                                                  billing_scope
                                                  via Vercel AI Gateway
                                                  Billing label
                                                  Input tokens / 1M
                                                  Pricing via
                                                  Vercel AI Gateway

                                                  openai/gpt-5-mini ↗

                                                  $2.00

                                                  Inference provider
                                                  vercelAIGatewayCatalog
                                                  Platform
                                                  azure
                                                  Unit
                                                  output_tokens_per_million
                                                  Currency
                                                  USD
                                                  Billing conditions
                                                  endpoint
                                                  azure | openai/gpt-5-mini
                                                  model_type
                                                  language
                                                  billing_scope
                                                  via Vercel AI Gateway
                                                  Billing label
                                                  Output tokens / 1M
                                                  Pricing via
                                                  Vercel AI Gateway

                                                  openai/gpt-5-mini ↗

                                                  $0.01

                                                  Inference provider
                                                  vercelAIGatewayCatalog
                                                  Platform
                                                  azure
                                                  Unit
                                                  request
                                                  Currency
                                                  USD
                                                  Billing conditions
                                                  charge
                                                  web_search
                                                  endpoint
                                                  azure | openai/gpt-5-mini
                                                  model_type
                                                  language
                                                  billing_scope
                                                  via Vercel AI Gateway
                                                  Billing label
                                                  Web search
                                                  Pricing via
                                                  Vercel AI Gateway

                                                  openai/gpt-5-mini ↗

                                                  $0.02

                                                  Inference provider
                                                  vercelAIGatewayCatalog
                                                  Platform
                                                  openai
                                                  Unit
                                                  cache_read_tokens_per_million
                                                  Currency
                                                  USD
                                                  Billing conditions
                                                  endpoint
                                                  openai | openai/gpt-5-mini
                                                  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-5-mini · azure-openai v2025-08-07 ↗

                                                  source model id
                                                  azure-openai/gpt-5-mini@2025-08-07
                                                  hosting
                                                  foundry-managed-compute
                                                  platforms
                                                  • Microsoft Foundry
                                                  license
                                                  custom
                                                  context length
                                                  400000
                                                  max input tokens
                                                  272000
                                                  max output tokens
                                                  128000
                                                  architecture
                                                  input_modalities
                                                  • text
                                                  • image
                                                  output_modalities
                                                  • text
                                                  capabilities
                                                  • reasoning
                                                  • toolCalling

                                                  gpt-5-mini ↗

                                                  source model id
                                                  gpt-5-mini
                                                  hosting
                                                  gateway
                                                  platforms
                                                  • Cheaper Inference
                                                  context length
                                                  400000
                                                  max output tokens
                                                  128000
                                                  architecture
                                                  input_modalities
                                                  • text
                                                  • image
                                                  output_modalities
                                                  • text
                                                  capabilities
                                                  • reasoning
                                                  • structuredOutputs
                                                  • toolCalling
                                                  • visionInput
                                                  • webSearch

                                                  GPT-5 mini ↗

                                                  source model id
                                                  openai/gpt-5-mini
                                                  hosting
                                                  third-party
                                                  platforms
                                                  • OpenAI
                                                  context length
                                                  128000
                                                  max output tokens
                                                  16384
                                                  architecture
                                                  input_modalities
                                                  • text
                                                  output_modalities
                                                  • text
                                                  capabilities

                                                    GPT-5 mini ↗

                                                    source model id
                                                    openai/gpt-5-mini
                                                    hosting
                                                    vercel-gateway
                                                    platforms
                                                    • Vercel AI Gateway
                                                    context length
                                                    400000
                                                    max output tokens
                                                    128000
                                                    architecture
                                                    input_modalities
                                                    • text
                                                    • image
                                                    • pdf
                                                    output_modalities
                                                    • text
                                                    capabilities
                                                    • promptCaching
                                                    • reasoning
                                                    • structuredOutputs
                                                    • toolCalling
                                                    • visionInput
                                                    • webSearch

                                                    Safety assessments

                                                    1–1 / 1

                                                    Foundation Model Transparency Index 2025 ↗

                                                    35 / 100

                                                    source id
                                                    stanfordFMTI
                                                    canonical model id
                                                    openai/gpt-5-mini-2025-08-07
                                                    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

                                                    1–15 / 15

                                                    azureFoundry ↗

                                                    field
                                                    context_length
                                                    value
                                                    400000
                                                    normalized value
                                                    400000
                                                    scope
                                                    source-model
                                                    source id
                                                    azureFoundry
                                                    confidence
                                                    1

                                                    cloudflareWorkersAI ↗

                                                    field
                                                    context_length
                                                    value
                                                    128000
                                                    normalized value
                                                    128000
                                                    scope
                                                    source-model
                                                    source id
                                                    cloudflareWorkersAI
                                                    confidence
                                                    1

                                                    openRouter ↗

                                                    field
                                                    context_length
                                                    value
                                                    400000
                                                    normalized value
                                                    400000
                                                    scope
                                                    source-model
                                                    source id
                                                    openRouter
                                                    confidence
                                                    1

                                                    openRouter ↗

                                                    field
                                                    context_length
                                                    value
                                                    400000
                                                    normalized value
                                                    400000
                                                    scope
                                                    source-model
                                                    source id
                                                    openRouter
                                                    confidence
                                                    1

                                                    vercelAIGatewayCatalog ↗

                                                    field
                                                    context_length
                                                    value
                                                    400000
                                                    normalized value
                                                    400000
                                                    scope
                                                    source-model
                                                    source id
                                                    vercelAIGatewayCatalog
                                                    confidence
                                                    1

                                                    openRouter ↗

                                                    field
                                                    knowledge_cutoff
                                                    reported field
                                                    knowledge_cutoff
                                                    value
                                                    2024-05-31
                                                    normalized value
                                                    2024-05-31
                                                    precision
                                                    day
                                                    scope
                                                    source-model
                                                    source id
                                                    openRouter
                                                    confidence
                                                    1

                                                    openRouter ↗

                                                    field
                                                    knowledge_cutoff
                                                    reported field
                                                    knowledge_cutoff
                                                    value
                                                    2024-05-31
                                                    normalized value
                                                    2024-05-31
                                                    precision
                                                    day
                                                    scope
                                                    source-model
                                                    source id
                                                    openRouter
                                                    confidence
                                                    1

                                                    vercelAIGatewayCatalog ↗

                                                    field
                                                    knowledge_cutoff
                                                    reported field
                                                    knowledge_cutoff
                                                    value
                                                    2024-05-31
                                                    normalized value
                                                    2024-05-31
                                                    precision
                                                    day
                                                    scope
                                                    source-model
                                                    source id
                                                    vercelAIGatewayCatalog
                                                    confidence
                                                    1

                                                    azureFoundry ↗

                                                    field
                                                    max_input_tokens
                                                    value
                                                    272000
                                                    normalized value
                                                    272000
                                                    scope
                                                    source-model
                                                    source id
                                                    azureFoundry
                                                    confidence
                                                    1

                                                    azureFoundry ↗

                                                    field
                                                    max_output_tokens
                                                    value
                                                    128000
                                                    normalized value
                                                    128000
                                                    scope
                                                    source-model
                                                    source id
                                                    azureFoundry
                                                    confidence
                                                    1

                                                    cloudflareWorkersAI ↗

                                                    field
                                                    max_output_tokens
                                                    value
                                                    16384
                                                    normalized value
                                                    16384
                                                    scope
                                                    source-model
                                                    source id
                                                    cloudflareWorkersAI
                                                    confidence
                                                    1

                                                    openRouter ↗

                                                    field
                                                    max_output_tokens
                                                    value
                                                    128000
                                                    normalized value
                                                    128000
                                                    scope
                                                    source-model
                                                    source id
                                                    openRouter
                                                    confidence
                                                    1

                                                    openRouter ↗

                                                    field
                                                    max_output_tokens
                                                    value
                                                    128000
                                                    normalized value
                                                    128000
                                                    scope
                                                    source-model
                                                    source id
                                                    openRouter
                                                    confidence
                                                    1

                                                    vercelAIGatewayCatalog ↗

                                                    field
                                                    max_output_tokens
                                                    value
                                                    128000
                                                    normalized value
                                                    128000
                                                    scope
                                                    source-model
                                                    source id
                                                    vercelAIGatewayCatalog
                                                    confidence
                                                    1

                                                    azureFoundry ↗

                                                    field
                                                    knowledge_cutoff
                                                    reported field
                                                    training_data_cutoff
                                                    value
                                                    June 2024
                                                    normalized value
                                                    2024-06
                                                    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