OpenAI: o4 Mini (batch)
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demons…
openai/o4-mini-2025-04-16
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.
Despite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.
Specifications & capabilities
- Input
- image, text, file
- Output
- text
- Context window · tokens
- 200000
- Published model ID
- o4-mini-2025-04-16
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗Evaluations
121–140 / 912
100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-104
- dimension
- reasoning
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-104
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 984153
- name
- gpqa-diamond-zero-shot/task-104
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 7
- name
- GPQA Diamond Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8176
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-104
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8176/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
- measurements
- name
- gpqa-diamond-zero-shot/task-104
- unit
- percent
- scale
- 1
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-104
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-12T18:13:19.5980168Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 984153
- sort_order
- DESCENDING
- source_name
- gpqa-diamond-zero-shot/task-104
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-12T17:49:58.132967500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 32
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-12T18:13:19.598Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-197
- dimension
- reasoning
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-197
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 984247
- name
- gpqa-diamond-zero-shot/task-197
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 7
- name
- GPQA Diamond Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8176
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-197
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8176/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
- measurements
- name
- gpqa-diamond-zero-shot/task-197
- unit
- percent
- scale
- 1
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-197
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-12T18:15:38.748265Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 984247
- sort_order
- DESCENDING
- source_name
- gpqa-diamond-zero-shot/task-197
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-12T17:49:58.132967500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 32
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-12T18:15:38.748Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-033
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-033
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071427
- name
- gpqa-main-zero-shot/task-033
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-033
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-033
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-033
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T18:13:53.4578693Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071427
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-033
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T18:13:53.457Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-329
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-329
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071756
- name
- gpqa-main-zero-shot/task-329
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-329
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-329
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-329
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T20:47:52.8713279Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071756
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-329
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T20:47:52.871Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-001
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-001
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071392
- name
- gpqa-main-zero-shot/task-001
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-001
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-001
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-001
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T17:23:25.8836155Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071392
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-001
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T17:23:25.883Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-218
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-218
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071638
- name
- gpqa-main-zero-shot/task-218
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-218
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-218
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-218
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:58:13.461822Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071638
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-218
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:58:13.461Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-443
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-443
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071883
- name
- gpqa-main-zero-shot/task-443
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-443
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-443
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-443
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T21:41:59.7106828Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071883
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-443
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T21:41:59.710Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-352
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-352
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071782
- name
- gpqa-main-zero-shot/task-352
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-352
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-352
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-352
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T20:57:58.7818319Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071782
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-352
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T20:57:58.781Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-062
- dimension
- reasoning
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-062
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 984111
- name
- gpqa-diamond-zero-shot/task-062
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 7
- name
- GPQA Diamond Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8176
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-062
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8176/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
- measurements
- name
- gpqa-diamond-zero-shot/task-062
- unit
- percent
- scale
- 1
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-062
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-12T18:12:08.6649934Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 984111
- sort_order
- DESCENDING
- source_name
- gpqa-diamond-zero-shot/task-062
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-12T17:49:58.132967500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 32
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-12T18:12:08.664Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-275
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-275
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071699
- name
- gpqa-main-zero-shot/task-275
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-275
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-275
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-275
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T20:21:44.3619148Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071699
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-275
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T20:21:44.361Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-099
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-099
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071502
- name
- gpqa-main-zero-shot/task-099
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-099
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-099
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-099
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:00:33.6697185Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071502
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-099
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:00:33.669Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-069
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-069
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071470
- name
- gpqa-main-zero-shot/task-069
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-069
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-069
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-069
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T18:39:24.8310008Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071470
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-069
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T18:39:24.831Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-002
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-002
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071393
- name
- gpqa-main-zero-shot/task-002
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-002
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-002
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-002
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T17:23:47.1110743Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071393
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-002
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T17:23:47.111Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-383
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-383
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071815
- name
- gpqa-main-zero-shot/task-383
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-383
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-383
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-383
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T21:09:41.7652125Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071815
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-383
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T21:09:41.765Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-432
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-432
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071872
- name
- gpqa-main-zero-shot/task-432
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-432
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-432
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-432
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T21:36:31.2583103Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071872
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-432
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T21:36:31.258Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-014
- dimension
- reasoning
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-014
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 984062
- name
- gpqa-diamond-zero-shot/task-014
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 7
- name
- GPQA Diamond Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8176
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-014
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8176/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
- measurements
- name
- gpqa-diamond-zero-shot/task-014
- unit
- percent
- scale
- 1
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-014
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-12T18:09:29.6723474Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 984062
- sort_order
- DESCENDING
- source_name
- gpqa-diamond-zero-shot/task-014
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-12T17:49:58.132967500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 32
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-12T18:09:29.672Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-013
- dimension
- reasoning
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-013
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 984061
- name
- gpqa-diamond-zero-shot/task-013
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 7
- name
- GPQA Diamond Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8176
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Diamond Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-013
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8176/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-diamond-set/versions/2
- measurements
- name
- gpqa-diamond-zero-shot/task-013
- unit
- percent
- scale
- 1
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-013
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-12T18:09:16.4653886Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 984061
- sort_order
- DESCENDING
- source_name
- gpqa-diamond-zero-shot/task-013
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-12T17:49:58.132967500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 32
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-12T18:09:16.465Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-118
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-118
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071525
- name
- gpqa-main-zero-shot/task-118
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-118
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-118
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-118
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:10:01.0941716Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071525
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-118
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:10:01.094Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-274
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-274
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071698
- name
- gpqa-main-zero-shot/task-274
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-274
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-274
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-274
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T20:22:16.8977434Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071698
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-274
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T20:22:16.897Z
- source model id
- o4 mini
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-268
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-268
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071692
- name
- gpqa-main-zero-shot/task-268
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 8
- name
- GPQA Main Zero‑Shot
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 2
- categories
- general knowledge and reasoning
- science
- version_id
- 8463
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · GPQA Main Zero‑Shot
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-268
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 8463/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/gpqa-zero-shot-main-set/versions/2
- measurements
- name
- gpqa-main-zero-shot/task-268
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-268
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T20:19:50.2512792Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 1071692
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-268
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-21T18:15:21.342276500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/o4-mini-2025-04-16
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T20:19:50.251Z
- source model id
- o4 mini
Original result ↗Published prices
1–15 / 15
$0.28
- Inference provider
- cloudflareWorkersAI
- Platform
- OpenAI
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing label
- Cached input tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$1.10
- Inference provider
- cloudflareWorkersAI
- Platform
- OpenAI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing label
- Input tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$4.40
- Inference provider
- cloudflareWorkersAI
- Platform
- OpenAI
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing label
- Output tokens (per 1M)
- Pricing via
- Cloudflare AI Gateway
$0.14
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$0.55
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$2.20
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- web_search
- Currency
- USD
- Billing conditions
- mode
- batch
$0.28
- Inference provider
- vercelAIGatewayCatalog
- Platform
- azure
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- azure | openai/o4-mini
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$1.10
- Inference provider
- vercelAIGatewayCatalog
- Platform
- azure
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- azure | openai/o4-mini
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$4.40
- Inference provider
- vercelAIGatewayCatalog
- Platform
- azure
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- azure | openai/o4-mini
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.01
- Inference provider
- vercelAIGatewayCatalog
- Platform
- azure
- Unit
- request
- Currency
- USD
- Billing conditions
- charge
- web_search
- endpoint
- azure | openai/o4-mini
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Web search
- Pricing via
- Vercel AI Gateway
$0.28
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$1.10
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$4.40
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.01
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- request
- Currency
- USD
- Billing conditions
- charge
- web_search
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Web search
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–3 / 3
- source model id
- azure-openai/o4-mini@2025-04-16
- hosting
- foundry-managed-compute
- license
- custom
- context length
- 200000
- max output tokens
- 100000
- source model id
- openai/o4-mini
- hosting
- third-party
- context length
- 200000
- max output tokens
- 100000
- source model id
- openai/o4-mini
- hosting
- vercel-gateway
- context length
- 200000
- max output tokens
- 100000
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
Safety assessments
1–1 / 1
35 / 100
- source id
- stanfordFMTI
- canonical model id
- openai/o4-mini-2025-04-16
- 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
1–11 / 11
- field
- context_length
- value
- 200000
- normalized value
- 200000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 200000
- normalized value
- 200000
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- context_length
- value
- 200000
- normalized value
- 200000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 200000
- normalized value
- 200000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-06-30
- normalized value
- 2024-06-30
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-06-01
- normalized value
- 2024-06-01
- precision
- day
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_output_tokens
- value
- 100000
- normalized value
- 100000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- max_output_tokens
- value
- 100000
- normalized value
- 100000
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- max_output_tokens
- value
- 100000
- normalized value
- 100000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 100000
- normalized value
- 100000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- training_data_cutoff
- value
- May 2024
- normalized value
- 2024-05
- precision
- month
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
Explore more models