OpenAI: GPT-5
GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction …
openai/gpt-5-2025-08-07
GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like "think hard about this." Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.
Specifications & capabilities
- Input
- text, image, file
- Output
- text
- Context window · tokens
- 400000
- Published model ID
- gpt-5-2025-08-07
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗Evaluations
1–20 / 913
100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-238
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-238
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071659
- name
- gpqa-main-zero-shot/task-238
- 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-238
- 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-238
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-238
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:36:09.2060571Z
- 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
- 1071659
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-238
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:36:09.206Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-418
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-418
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071857
- name
- gpqa-main-zero-shot/task-418
- 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-418
- 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-418
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-418
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T20:07:58.9740924Z
- 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
- 1071857
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-418
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T20:07:58.974Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-369
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-369
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071801
- name
- gpqa-main-zero-shot/task-369
- 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-369
- 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-369
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-369
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:59:52.6676697Z
- 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
- 1071801
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-369
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:59:52.667Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-087
- dimension
- reasoning
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-087
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 984136
- name
- gpqa-diamond-zero-shot/task-087
- 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-087
- 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-087
- unit
- percent
- scale
- 1
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-087
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-12T18:12:25.6906046Z
- 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
- 984136
- sort_order
- DESCENDING
- source_name
- gpqa-diamond-zero-shot/task-087
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-12T17:49:58.132967500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-5-2025-08-07
- metric_population
- 32
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-12T18:12:25.690Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-156
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-156
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071569
- name
- gpqa-main-zero-shot/task-156
- 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-156
- 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-156
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-156
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:12:21.0975722Z
- 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
- 1071569
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-156
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:12:21.097Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-021
- dimension
- reasoning
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-021
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 984069
- name
- gpqa-diamond-zero-shot/task-021
- 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-021
- 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-021
- unit
- percent
- scale
- 1
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-021
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-12T18:09:25.43737Z
- 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
- 984069
- sort_order
- DESCENDING
- source_name
- gpqa-diamond-zero-shot/task-021
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-12T17:49:58.132967500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-5-2025-08-07
- metric_population
- 32
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-12T18:09:25.437Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-288
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-288
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071713
- name
- gpqa-main-zero-shot/task-288
- 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-288
- 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-288
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-288
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:44:14.4251297Z
- 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
- 1071713
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-288
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:44:14.425Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-073
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-073
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071475
- name
- gpqa-main-zero-shot/task-073
- 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-073
- 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-073
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-073
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T18:42:19.8340988Z
- 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
- 1071475
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-073
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T18:42:19.834Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-101
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-101
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071504
- name
- gpqa-main-zero-shot/task-101
- 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-101
- 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-101
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-101
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T18:58:31.2616733Z
- 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
- 1071504
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-101
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T18:58:31.261Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-342
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-342
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071771
- name
- gpqa-main-zero-shot/task-342
- 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-342
- 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-342
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-342
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:54:22.4082968Z
- 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
- 1071771
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-342
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:54:22.408Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-419
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-419
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071858
- name
- gpqa-main-zero-shot/task-419
- 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-419
- 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-419
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-419
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T20:10:27.003578Z
- 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
- 1071858
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-419
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T20:10:27.003Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-250
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-250
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071671
- name
- gpqa-main-zero-shot/task-250
- 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-250
- 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-250
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-250
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:38:10.2931803Z
- 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
- 1071671
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-250
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:38:10.293Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-336
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-336
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071765
- name
- gpqa-main-zero-shot/task-336
- 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-336
- 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-336
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-336
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:53:57.9227704Z
- 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
- 1071765
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-336
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:53:57.922Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-153
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-153
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071566
- name
- gpqa-main-zero-shot/task-153
- 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-153
- 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-153
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-153
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:12:16.6492096Z
- 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
- 1071566
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-153
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:12:16.649Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-320
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-320
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071747
- name
- gpqa-main-zero-shot/task-320
- 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-320
- 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-320
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-320
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:50:40.1618841Z
- 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
- 1071747
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-320
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:50:40.161Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-007
- dimension
- reasoning
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-007
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 984055
- name
- gpqa-diamond-zero-shot/task-007
- 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-007
- 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-007
- unit
- percent
- scale
- 1
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-007
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-12T18:10:00.5033806Z
- 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
- 984055
- sort_order
- DESCENDING
- source_name
- gpqa-diamond-zero-shot/task-007
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-12T17:49:58.132967500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-5-2025-08-07
- metric_population
- 32
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-12T18:10:00.503Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-433
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-433
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071873
- name
- gpqa-main-zero-shot/task-433
- 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-433
- 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-433
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-433
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T20:15:17.9086246Z
- 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
- 1071873
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-433
- 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/gpt-5-2025-08-07
- metric_population
- 25
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T20:15:17.908Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-261
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-261
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071683
- name
- gpqa-main-zero-shot/task-261
- 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-261
- 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-261
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-261
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:39:19.7937074Z
- 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
- 1071683
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-261
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:39:19.793Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-176
- dimension
- reasoning
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-176
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 984226
- name
- gpqa-diamond-zero-shot/task-176
- 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-176
- 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-176
- unit
- percent
- scale
- 1
- metric
- GPQA Diamond Zero‑Shot · gpqa-diamond-zero-shot/task-176
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-12T18:15:50.5244578Z
- 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
- 984226
- sort_order
- DESCENDING
- source_name
- gpqa-diamond-zero-shot/task-176
- display_type
- percentages
- task_version
- 1
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2026-10-12T17:49:58.132967500Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-5-2025-08-07
- metric_population
- 32
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-12T18:15:50.524Z
- source model id
- GPT-5
Original result ↗100%
- source id
- kaggleBenchmarks
- leaderboard name
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-223
- dimension
- reasoning
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-223
- rank
- 1
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 1071643
- name
- gpqa-main-zero-shot/task-223
- 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-223
- 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-223
- unit
- percent
- scale
- 1
- metric
- GPQA Main Zero‑Shot · gpqa-main-zero-shot/task-223
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 1
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2026-10-20T19:31:21.0116087Z
- 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
- 1071643
- sort_order
- DESCENDING
- source_name
- gpqa-main-zero-shot/task-223
- 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/gpt-5-2025-08-07
- metric_population
- 26
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2026-10-20T19:31:21.011Z
- source model id
- GPT-5
Original result ↗Published prices
41–42 / 42
$20.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- priority
- billing_scope
- Vercel public catalog; endpoint prices may differ
- varies_by_provider
- true
- 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
- varies_by_provider
- true
- Billing label
- Web search
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–4 / 4
- source model id
- azure-openai/gpt-5@2025-08-07
- hosting
- foundry-managed-compute
- license
- custom
- context length
- 400000
- max input tokens
- 272000
- max output tokens
- 128000
- source model id
- gpt-5
- hosting
- gateway
- context length
- 400000
- max output tokens
- 128000
- capabilities
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
- source model id
- openai/gpt-5
- hosting
- third-party
- context length
- 128000
- max output tokens
- 16384
- source model id
- openai/gpt-5
- hosting
- vercel-gateway
- context length
- 400000
- max output tokens
- 128000
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
Safety assessments
1–1 / 1
35 / 100
- source id
- stanfordFMTI
- canonical model id
- openai/gpt-5-2025-08-07
- 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
- field
- context_length
- value
- 400000
- normalized value
- 400000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- context_length
- value
- 400000
- normalized value
- 400000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 400000
- normalized value
- 400000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 400000
- normalized value
- 400000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-09-30
- normalized value
- 2024-09-30
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-09-30
- normalized value
- 2024-09-30
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-09-30
- normalized value
- 2024-09-30
- precision
- day
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_input_tokens
- value
- 272000
- normalized value
- 272000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- max_output_tokens
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- training_data_cutoff
- value
- October 2024
- normalized value
- 2024-10
- precision
- month
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
Explore more models