OpenAI: GPT-4o-mini (2024-07-18)
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more …
openai/gpt-4o-mini-2024-07-18
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...
Specifications & capabilities
- Input
- text, image, file
- Output
- text
- Context window · tokens
- 128000
- Capabilities
- audioInput, fileInput, multimodal, promptCaching, structuredOutputs, toolCalling, visionInput
Evaluations
61–80 / 186
78.158%
- source id
- helm
- leaderboard name
- HELM IFEval
- dimension
- agentic
- metric
- ifeval_strict_accuracy
- rank
- 52
- sample size
- 541
- source model id
- openai/gpt-4o-mini-2024-07-18
Original result ↗62.367%
- source id
- kaggleBenchmarks
- leaderboard name
- MMLU-Pro · mmlu_pro_task
- dimension
- reasoning
- metric
- MMLU-Pro · mmlu_pro_task
- rank
- 53
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 40138
- name
- mmlu_pro_task
- version
- 12
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 44
- name
- MMLU-Pro
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 1
- categories
- general knowledge and reasoning
- version_id
- 30
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · MMLU-Pro
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MMLU-Pro · mmlu_pro_task
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 30/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/mmlu-pro/versions/1
- measurements
- name
- mmlu_pro_task
- unit
- percent
- scale
- 1
- metric
- MMLU-Pro · mmlu_pro_task
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.6236702127659575
- standardDeviation
- 0
- confidenceInterval
- 0.0086564729829687
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0086564729829687
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-13T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.6236702127659575
- standardDeviation
- 0
- confidenceInterval
- 0.0086564729829687
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0086564729829687
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 40138
- task_url
- /benchmarks/tasks/benchmarkler/mmlu-pro-task
- sort_order
- DESCENDING
- source_name
- mmlu_pro_task
- display_type
- percentages
- task_version
- 12
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-mini-2024-07-18
- metric_population
- 64
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-13T00:00:00.000Z
- source model id
- GPT-4o mini
- confidence lower
- 0.6150137397829888
- confidence upper
- 0.6323266857489261
Original result ↗36.771%
- source id
- helm
- leaderboard name
- HELM GPQA
- dimension
- intelligence
- metric
- chain_of_thought_correctness
- rank
- 53
- sample size
- 446
- source model id
- openai/gpt-4o-mini-2024-07-18
Original result ↗16.495%
- source id
- kaggleBenchmarks
- leaderboard name
- SciCode · SciCode Subproblem Standard
- dimension
- coding
- metric
- SciCode · SciCode Subproblem Standard
- rank
- 53
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 40106
- name
- SciCode Subproblem Standard
- version
- 3
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 16
- name
- SciCode
- type
- SUITE
- owner
- open-benchmarks
- version
- 1
- categories
- general knowledge and reasoning
- coding
- science
- version_id
- 16
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · SciCode
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- SciCode · SciCode Subproblem Standard
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 16/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/scicode/versions/1
- measurements
- name
- SciCode Subproblem Standard
- unit
- percent
- scale
- 1
- metric
- SciCode · SciCode Subproblem Standard
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.1649484536082474
- standardDeviation
- 0
- confidenceInterval
- 0.0426414891568138
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0426414891568138
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-05-22T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.1649484536082474
- standardDeviation
- 0
- confidenceInterval
- 0.0426414891568138
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0426414891568138
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 40106
- task_url
- /benchmarks/open-benchmarks/scicode-subproblem-standard/versions/1
- sort_order
- DESCENDING
- source_name
- SciCode Subproblem Standard
- display_type
- percentages
- task_version
- 3
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2025-10-21T20:29:26.251536900Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-mini-2024-07-18
- metric_population
- 62
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-05-22T00:00:00.000Z
- source model id
- GPT-4o mini
- confidence lower
- 0.12230696445143359
- confidence upper
- 0.2075899427650612
Original result ↗24.055%
- source id
- kaggleBenchmarks
- leaderboard name
- SciCode · SciCode Subproblem With Background
- dimension
- coding
- metric
- SciCode · SciCode Subproblem With Background
- rank
- 54
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 40200
- name
- SciCode Subproblem With Background
- version
- 3
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 16
- name
- SciCode
- type
- SUITE
- owner
- open-benchmarks
- version
- 1
- categories
- general knowledge and reasoning
- coding
- science
- version_id
- 16
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · SciCode
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- SciCode · SciCode Subproblem With Background
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 16/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/scicode/versions/1
- measurements
- name
- SciCode Subproblem With Background
- unit
- percent
- scale
- 1
- metric
- SciCode · SciCode Subproblem With Background
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.2405498281786941
- standardDeviation
- 0
- confidenceInterval
- 0.0491081715605116
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0491081715605116
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-05-22T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.2405498281786941
- standardDeviation
- 0
- confidenceInterval
- 0.0491081715605116
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0491081715605116
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 40200
- task_url
- /benchmarks/open-benchmarks/scicode-subproblem-with-background/versions/1
- sort_order
- DESCENDING
- source_name
- SciCode Subproblem With Background
- display_type
- percentages
- task_version
- 3
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2025-10-21T20:29:26.251536900Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-mini-2024-07-18
- metric_population
- 62
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-05-22T00:00:00.000Z
- source model id
- GPT-4o mini
- confidence lower
- 0.19144165661818252
- confidence upper
- 0.2896579997392057
Original result ↗0%
- source id
- kaggleBenchmarks
- leaderboard name
- SciCode · SciCode Main With Background
- dimension
- coding
- metric
- SciCode · SciCode Main With Background
- rank
- 54
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 40201
- name
- SciCode Main With Background
- version
- 3
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 16
- name
- SciCode
- type
- SUITE
- owner
- open-benchmarks
- version
- 1
- categories
- general knowledge and reasoning
- coding
- science
- version_id
- 16
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · SciCode
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- SciCode · SciCode Main With Background
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 16/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/scicode/versions/1
- measurements
- name
- SciCode Main With Background
- unit
- percent
- scale
- 1
- metric
- SciCode · SciCode Main With Background
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-05-22T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 40201
- task_url
- /benchmarks/open-benchmarks/scicode-main-with-background/versions/1
- sort_order
- DESCENDING
- source_name
- SciCode Main With Background
- display_type
- percentages
- task_version
- 3
- task_display_type
- RAW_VALUES
- normalization_status
- normalized
- published_at
- 2025-10-21T20:29:26.251536900Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-mini-2024-07-18
- metric_population
- 62
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-05-22T00:00:00.000Z
- source model id
- GPT-4o mini
- confidence lower
- 0
- confidence upper
- 0
Original result ↗8.333%
- source id
- kaggleBenchmarks
- leaderboard name
- AIME 2025 · aime_task
- dimension
- math
- metric
- AIME 2025 · aime_task
- rank
- 56
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 40087
- name
- aime_task
- version
- 6
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 125
- name
- AIME 2025
- type
- INDIVIDUAL
- owner
- open-benchmarks
- version
- 1
- categories
- general knowledge and reasoning
- math
- version_id
- 111
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · open-benchmarks · AIME 2025
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- AIME 2025 · aime_task
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 111/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/open-benchmarks/aime-2025/versions/1
- measurements
- name
- aime_task
- unit
- percent
- scale
- 1
- metric
- AIME 2025 · aime_task
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.0833333333333333
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-07-07T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.0833333333333333
- standardDeviation
- 0
- confidenceInterval
- 0
- hasStandardDeviation
- false
- hasConfidenceInterval
- false
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 40087
- task_url
- /benchmarks/tasks/benchmarkler/aime-task
- sort_order
- DESCENDING
- source_name
- aime_task
- display_type
- percentages
- task_version
- 6
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-mini-2024-07-18
- metric_population
- 68
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-07-07T00:00:00.000Z
- source model id
- GPT-4o mini
Original result ↗42.969%
- source id
- liveBench
- leaderboard name
- LiveBench Coding
- dimension
- coding
- metric
- Average score
- rank
- 64
- sample size
- 128
- evaluated at
- 2024-12-10T19:07:22.196Z
- source model id
- gpt-4o-mini-2024-07-18
Original result ↗40.569%
- source id
- liveBench
- leaderboard name
- LiveBench Overall
- dimension
- general
- metric
- Average score
- rank
- 81
- sample size
- 494
- evaluated at
- 2025-02-06T20:22:03.643Z
- source model id
- gpt-4o-mini-2024-07-18
Original result ↗32.897%
- source id
- liveBench
- leaderboard name
- LiveBench Language
- dimension
- intelligence
- metric
- Average score
- rank
- 86
- sample size
- 290
- evaluated at
- 2025-02-06T20:22:03.643Z
- source model id
- gpt-4o-mini-2024-07-18
Original result ↗65.8%
- source id
- liveBench
- leaderboard name
- LiveBench Instruction Following
- dimension
- general
- metric
- Average score
- rank
- 88
- sample size
- 76
- evaluated at
- 2024-12-10T19:31:50.186Z
- source model id
- gpt-4o-mini-2024-07-18
Original result ↗1,079.616
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Chinese
- dimension
- multimodal
- metric
- Arena rating
- rank
- 118
- sample size
- 954
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-4o mini (2024-07-18)
- confidence lower
- 1041.20624039325
- confidence upper
- 1118.0265944714952
Original result ↗1,032.919
- source id
- lmarena
- leaderboard name
- LMArena Vision Chinese
- dimension
- multimodal
- metric
- Arena rating
- rank
- 119
- sample size
- 954
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-4o mini (2024-07-18)
- confidence lower
- 994.6947016245197
- confidence upper
- 1071.14357762672
Original result ↗1,097.03
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Overall
- dimension
- multimodal
- metric
- Arena rating
- rank
- 137
- sample size
- 17341
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-4o mini (2024-07-18)
- confidence lower
- 1088.7004133134449
- confidence upper
- 1105.3587810434972
Original result ↗1,065.513
- source id
- lmarena
- leaderboard name
- LMArena Vision Overall
- dimension
- multimodal
- metric
- Arena rating
- rank
- 137
- sample size
- 17341
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-4o mini (2024-07-18)
- confidence lower
- 1057.1690526135899
- confidence upper
- 1073.8562384384722
Original result ↗1,072.234
- source id
- lmarena
- leaderboard name
- LMArena Vision English
- dimension
- multimodal
- metric
- Arena rating
- rank
- 138
- sample size
- 10721
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-4o mini (2024-07-18)
- confidence lower
- 1061.3559412544573
- confidence upper
- 1083.1113119826582
Original result ↗1,096.991
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control English
- dimension
- multimodal
- metric
- Arena rating
- rank
- 139
- sample size
- 10721
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-4o mini (2024-07-18)
- confidence lower
- 1086.1270584714819
- confidence upper
- 1107.8543012425089
Original result ↗1,215.871
- source id
- lmarena
- leaderboard name
- LMArena Text Japanese
- dimension
- general
- metric
- Arena rating
- rank
- 206
- sample size
- 1793
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-4o mini (2024-07-18)
- confidence lower
- 1200.2965190924679
- confidence upper
- 1231.4456663002452
Original result ↗1,250.667
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Japanese
- dimension
- style
- metric
- Arena rating
- rank
- 208
- sample size
- 1793
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-4o mini (2024-07-18)
- confidence lower
- 1234.9393417634449
- confidence upper
- 1266.393881384588
Original result ↗1,296.452
- source id
- lmarena
- leaderboard name
- LMArena Text French
- dimension
- general
- metric
- Arena rating
- rank
- 217
- sample size
- 649
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- GPT-4o mini (2024-07-18)
- confidence lower
- 1271.8946691969795
- confidence upper
- 1321.0085304049674
Original result ↗Published prices
1–3 / 3
$0.08
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$0.15
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.60
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
Provider specifications & access
1–1 / 1
- source model id
- azure-openai/gpt-4o-mini@2024-07-18
- hosting
- foundry-managed-compute
- license
- custom
- context length
- 128000
- max input tokens
- 128000
- max output tokens
- 16384
Safety assessments
1–1 / 1
35 / 100
- source id
- stanfordFMTI
- canonical model id
- openai/gpt-4o-mini-2024-07-18
- 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
1–7 / 7
- field
- context_length
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2023-10-31
- normalized value
- 2023-10-31
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_input_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
- azureFoundry
- confidence
- 1
- field
- max_output_tokens
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- training_data_cutoff
- value
- September 2023
- normalized value
- 2023-09
- precision
- month
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
Explore more models