o3-pro
Not tested yet
Language modelActive
o3-pro
OpenAI
- Released
- June 10, 2025
- Data date
- September 8, 2026
- Intelligence
- Overall score
- Price
- Input · Output / 1M tokens
- Input
- Text, Image
- Output
- Text
No published category-wide ranking is available for this model.
Entries 1-12 of 18. Page 1 of 2.
Published benchmarks
Each chart compares models in the same documented test and highlights the current model.
Aider Polyglot
Overall
What this benchmark measures: 225 code-editing tasks from Exercism across C++, Go, Java, JavaScript, Python, and Rust.
Context: Aider, the edit format, reasoning budget, and two attempts are part of the result.
Higher is better4 modelso3-pro: Rank 1 of 4Data date: September 2, 2026
Scale: 0% - 100%
Methodology and context
- Comparison cohort
- aider-polyglot-pass2-diff
- Metric
- percent correct after two attempts
- Scale
- 0-100
- Participants
- 4
- Methodology and context
- 225 Exercism tasks across six languages using Aider and a documented edit format.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Aider. Dataset type: public. Leaderboard date: 2025-06-28. Attempts: pass 2. Reasoning effort: high. Latency in seconds: 449. Cost per task in USD: 0.650332888888889. Source ID: aider. Evidence capture ID: curated-aider-2026-09-02-e7013fef86d5. Source payload hash: e7013fef86d5b6387e7d15e6603f3ef40570c3b4912902fafd102ce39a280110. Parser version: curated-v1. Imported at: 2026-09-04
MultiChallenge
Overall
What this benchmark measures: Multi-turn conversations test memory, instruction retention, versioned editing, and self-coherence.
Context: Tasks were selected from shared failures of six older frontier models and may disadvantage those systems.
Higher is better8 modelso3-pro: Rank 4 of 8Data date: August 26, 2026
Scale: 0% - 100%
Methodology and context
- Comparison cohort
- scale-multichallenge-overall
- Metric
- rubric pass rate
- Scale
- 0-100
- Participants
- 8
- Methodology and context
- Multi-turn conversations with binary task-specific rubrics.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Reasoning effort: high. Score display: 62.4% ± 2.49. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-658a3e008a02. Source payload hash: 658a3e008a023110d3ccb0ba0342e3d55eb690fea0e546fd5c644a1287842ce7. Parser version: curated-v1. Imported at: 2026-09-04
MultiNRC
Overall
What this benchmark measures: Native reasoning tasks in French, Spanish, and Chinese that were not translated from English templates.
Context: Three languages counter English-only evaluation, but they do not represent global language coverage.
Higher is better10 modelso3-pro: Rank 6 of 10Data date: August 26, 2026
Scale: 0% - 100%
Methodology and context
- Comparison cohort
- scale-multinrc-native-languages
- Metric
- accuracy
- Scale
- 0-100
- Participants
- 10
- Methodology and context
- Native, non-translated reasoning tasks with automatic evaluation.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Reasoning effort: high. Score display: 49% ± 3.02. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-145f9b03fae8. Source payload hash: 145f9b03fae81a57d6da422e17ffd143e4dd7869da95b1408b0f8ce896b4246a. Parser version: curated-v1. Imported at: 2026-09-04
PRBench Finance
Overall
What this benchmark measures: 600 realistic finance questions with weighted criteria, including a 300-question hard subset.
Context: An o4-mini judge scores the responses, so domain correctness and operational reliability remain separate questions.
Higher is better16 modelso3-pro: Rank 6 of 16Data date: August 26, 2026
Scale: 0% - 100%
Methodology and context
- Comparison cohort
- scale-prbench-finance-full
- Metric
- weighted rubric score
- Scale
- 0-100
- Participants
- 16
- Methodology and context
- 600 finance tasks with task-specific rubrics and o4-mini as judge.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Score display: 49.08% ± 0.79. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-a15dd5860124. Source payload hash: a15dd5860124c5d2805f234fc9e99880171cd19f76f66cacf63f4ab21a846ef0. Parser version: curated-v1. Imported at: 2026-09-04
PRBench Legal
Overall
What this benchmark measures: 500 realistic legal questions with weighted criteria across jurisdictions and practice areas.
Context: The benchmark measures professional response quality but cannot replace legal review or human accountability.
Higher is better16 modelso3-pro: Rank 5 of 16Data date: August 26, 2026
Scale: 0% - 100%
Methodology and context
- Comparison cohort
- scale-prbench-legal-full
- Metric
- weighted rubric score
- Scale
- 0-100
- Participants
- 16
- Methodology and context
- 500 legal tasks with task-specific rubrics and o4-mini as judge.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Score display: 49.67% ± 0.5. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-e1dcf6ae7d33. Source payload hash: e1dcf6ae7d33b234307f8bd4ba4bb133394e4cbca8c6ada0a92a5d927367d961. Parser version: curated-v1. Imported at: 2026-09-04
TutorBench
Overall
What this benchmark measures: 1,490 tasks test adaptive explanations, feedback, and hints across six STEM subjects.
Context: A Claude 4 Sonnet judge scores weighted rubrics, so strong results do not prove safe tutoring of real learners.
Higher is better8 modelso3-pro: Rank 4 of 8Data date: August 26, 2026
Scale: 0% - 100%
Methodology and context
- Comparison cohort
- scale-tutorbench-overall
- Metric
- weighted rubric score
- Scale
- 0-100
- Participants
- 8
- Methodology and context
- 1,490 tasks with weighted rubrics and Claude 4 Sonnet as judge.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Score display: 54.62% ± 1.02. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-7a86c0e52382. Source payload hash: 7a86c0e52382f7157e90b4a75ffca0e79c104460ae4ac971206896a283b99856. Parser version: curated-v1. Imported at: 2026-09-04
VISTA
Overall
What this benchmark measures: 758 image-text tasks combine OCR, spatial understanding, object recognition, and open-ended visual reasoning.
Context: The dataset is private and uses task-specific rubrics, making independent reproduction difficult.
Higher is better11 modelso3-pro: Rank 4 of 11Data date: August 26, 2026
Scale: 0% - 100%
Methodology and context
- Comparison cohort
- scale-vista-private-overall
- Metric
- rubric score
- Scale
- 0-100
- Participants
- 11
- Methodology and context
- 758 single-turn image-text tasks with structured yes-no rubrics.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Reasoning effort: high. Score display: 51.63% ± 0.25. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-8a92ee7cf963. Source payload hash: 8a92ee7cf963b85d0a28682e186b6062fef61e9317b71ec8603f644cdb8020fd. Parser version: curated-v1. Imported at: 2026-09-04
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
o3-pro win rate vs o3 - All Queries (Show measurement, test conditions, and source)
- Source value
- 64
- Score
- 64
- Metric
- percent
- Unit
- %
- Category
- Human preference
- Direction
- Higher is better
- Comparison cohort
- research:o3-pro:0
- Source type
- vendor-reported
- Evaluator
- OpenAI
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. o3-pro vs o3; human testers; point estimate
o3-pro win rate vs o3 - Scientific Analysis (Show measurement, test conditions, and source)
- Source value
- 64.9
- Score
- 64.9
- Metric
- percent
- Unit
- %
- Category
- Human preference
- Direction
- Higher is better
- Comparison cohort
- research:o3-pro:1
- Source type
- vendor-reported
- Evaluator
- OpenAI
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. o3-pro vs o3; human testers; point estimate
o3-pro win rate vs o3 - Personal Writing (Show measurement, test conditions, and source)
- Source value
- 66.7
- Score
- 66.7
- Metric
- percent
- Unit
- %
- Category
- Human preference
- Direction
- Higher is better
- Comparison cohort
- research:o3-pro:2
- Source type
- vendor-reported
- Evaluator
- OpenAI
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. o3-pro vs o3; human testers; point estimate
o3-pro win rate vs o3 - Computer Programming (Show measurement, test conditions, and source)
- Source value
- 62.7
- Score
- 62.7
- Metric
- percent
- Unit
- %
- Category
- Human preference
- Direction
- Higher is better
- Comparison cohort
- research:o3-pro:3
- Source type
- vendor-reported
- Evaluator
- OpenAI
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. o3-pro vs o3; human testers; point estimate
o3-pro win rate vs o3 - Data Analysis (Show measurement, test conditions, and source)
- Source value
- 64.3
- Score
- 64.3
- Metric
- percent
- Unit
- %
- Category
- Human preference
- Direction
- Higher is better
- Comparison cohort
- research:o3-pro:4
- Source type
- vendor-reported
- Evaluator
- OpenAI
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. o3-pro vs o3; human testers; point estimate
Recorded measurement details
Every observation retains its source value and published test conditions.
Aider Polyglot: Overall (Show measurement, test conditions, and source)
- Source value
- 84.9
- Score
- 84.9
- Metric
- percent correct after two attempts
- Unit
- %
- Benchmark version
- 225-case polyglot suite
- Category
- coding
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- aider-polyglot-pass2-diff
- Source type
- official-leaderboard
- Evaluator
- Aider
- Status
- active
- Retrieved at
- 2026-09-02
- Methodology
- 225 Exercism tasks across six languages using Aider and a documented edit format.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Aider. Dataset type: public. Leaderboard date: 2025-06-28. Attempts: pass 2. Reasoning effort: high. Latency in seconds: 449. Cost per task in USD: 0.650332888888889. Source ID: aider. Evidence capture ID: curated-aider-2026-09-02-e7013fef86d5. Source payload hash: e7013fef86d5b6387e7d15e6603f3ef40570c3b4912902fafd102ce39a280110. Parser version: curated-v1. Imported at: 2026-09-04
- Comparison methodology
- 225 Exercism tasks across six languages using Aider and a documented edit format.
MultiChallenge: Overall (Show measurement, test conditions, and source)
- Source value
- 62.4
- Score
- 62.4
- Metric
- rubric pass rate
- Unit
- %
- Benchmark version
- four multi-turn challenge types
- Category
- productivity
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- scale-multichallenge-overall
- Confidence interval
- 2.49
- Source type
- official-leaderboard
- Evaluator
- Scale AI
- Status
- active
- Retrieved at
- 2026-08-26
- Methodology
- Multi-turn conversations with binary task-specific rubrics.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Reasoning effort: high. Score display: 62.4% ± 2.49. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-658a3e008a02. Source payload hash: 658a3e008a023110d3ccb0ba0342e3d55eb690fea0e546fd5c644a1287842ce7. Parser version: curated-v1. Imported at: 2026-09-04
- Comparison methodology
- Multi-turn conversations with binary task-specific rubrics.
MultiNRC: Overall (Show measurement, test conditions, and source)
- Source value
- 49
- Score
- 49
- Metric
- accuracy
- Unit
- %
- Benchmark version
- French, Spanish, and Chinese release
- Category
- reasoning
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- scale-multinrc-native-languages
- Confidence interval
- 3.02
- Source type
- official-leaderboard
- Evaluator
- Scale AI
- Status
- active
- Retrieved at
- 2026-08-26
- Methodology
- Native, non-translated reasoning tasks with automatic evaluation.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Reasoning effort: high. Score display: 49% ± 3.02. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-145f9b03fae8. Source payload hash: 145f9b03fae81a57d6da422e17ffd143e4dd7869da95b1408b0f8ce896b4246a. Parser version: curated-v1. Imported at: 2026-09-04
- Comparison methodology
- Native, non-translated reasoning tasks with automatic evaluation.
PRBench Finance: Overall (Show measurement, test conditions, and source)
- Source value
- 49.08
- Score
- 49.08
- Metric
- weighted rubric score
- Unit
- %
- Benchmark version
- full finance set
- Category
- finance
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- scale-prbench-finance-full
- Confidence interval
- 0.79
- Source type
- official-leaderboard
- Evaluator
- Scale AI
- Status
- active
- Retrieved at
- 2026-08-26
- Methodology
- 600 finance tasks with task-specific rubrics and o4-mini as judge.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Score display: 49.08% ± 0.79. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-a15dd5860124. Source payload hash: a15dd5860124c5d2805f234fc9e99880171cd19f76f66cacf63f4ab21a846ef0. Parser version: curated-v1. Imported at: 2026-09-04
- Comparison methodology
- 600 finance tasks with task-specific rubrics and o4-mini as judge.
PRBench Legal: Overall (Show measurement, test conditions, and source)
- Source value
- 49.67
- Score
- 49.67
- Metric
- weighted rubric score
- Unit
- %
- Benchmark version
- full legal set
- Category
- legal
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- scale-prbench-legal-full
- Confidence interval
- 0.5
- Source type
- official-leaderboard
- Evaluator
- Scale AI
- Status
- active
- Retrieved at
- 2026-08-26
- Methodology
- 500 legal tasks with task-specific rubrics and o4-mini as judge.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Score display: 49.67% ± 0.5. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-e1dcf6ae7d33. Source payload hash: e1dcf6ae7d33b234307f8bd4ba4bb133394e4cbca8c6ada0a92a5d927367d961. Parser version: curated-v1. Imported at: 2026-09-04
- Comparison methodology
- 500 legal tasks with task-specific rubrics and o4-mini as judge.
TutorBench: Overall (Show measurement, test conditions, and source)
- Source value
- 54.62
- Score
- 54.62
- Metric
- weighted rubric score
- Unit
- %
- Benchmark version
- 1,490-task release
- Category
- education
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- scale-tutorbench-overall
- Confidence interval
- 1.02
- Source type
- official-leaderboard
- Evaluator
- Scale AI
- Status
- active
- Retrieved at
- 2026-08-26
- Methodology
- 1,490 tasks with weighted rubrics and Claude 4 Sonnet as judge.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Score display: 54.62% ± 1.02. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-7a86c0e52382. Source payload hash: 7a86c0e52382f7157e90b4a75ffca0e79c104460ae4ac971206896a283b99856. Parser version: curated-v1. Imported at: 2026-09-04
- Comparison methodology
- 1,490 tasks with weighted rubrics and Claude 4 Sonnet as judge.
VISTA: Overall (Show measurement, test conditions, and source)
- Source value
- 51.63
- Score
- 51.63
- Metric
- rubric score
- Unit
- %
- Benchmark version
- 758 private prompt-image pairs
- Category
- multimodal
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- scale-vista-private-overall
- Confidence interval
- 0.25
- Source type
- official-leaderboard
- Evaluator
- Scale AI
- Status
- active
- Retrieved at
- 2026-08-26
- Methodology
- 758 single-turn image-text tasks with structured yes-no rubrics.. Source model ID: curated/o3-pro. Source model name: o3-pro. Provider reported by source: OpenAI. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Reasoning effort: high. Score display: 51.63% ± 0.25. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-8a92ee7cf963. Source payload hash: 8a92ee7cf963b85d0a28682e186b6062fef61e9317b71ec8603f644cdb8020fd. Parser version: curated-v1. Imported at: 2026-09-04
- Comparison methodology
- 758 single-turn image-text tasks with structured yes-no rubrics.
Our model tests
Community tests you can inspect
Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.
Pelican on a bicycle
A community classic for free-form SVG drawing.
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)Profile
Specifications and access
Published information about this model. Existing estimates are explicitly labeled.
Additional source observations
Dated documentation and model-card observations. Provider limits, native context and extended context can differ. Configuration notes retain the source wording.
Pricing
Published prices
Prices apply to the stated unit. Resolution, output length, and provider can change the cost.
Cost example
100 API requests
$6
100 requests with 1,000 input and 500 output tokens each calculate to $6. Input accounts for $2; output accounts for $4.
- Input price
- $20 / 1M tokensBase tier for each request
- Output price
- $80 / 1M tokensBase tier for each request
The calculation uses documented token prices and no cache discount. It excludes extra tools, tax, reasoning tokens, and further hidden output tokens.
Open sourceHead-to-head comparisons
Compare this model
Each matchup compares this model with exactly one other model from the same category.
There are no published direct comparisons for this model yet.
Evidence
Sources and data date
Every statement links to its underlying documentation or leaderboard.
- Price
Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs.
- Input
Documented modalities. Retrieved September 8, 2026.
- Output
Documented modalities. Retrieved September 8, 2026.
Research date September 8, 2026. 7 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Open evidence questions and research notes (original wording)
Not found in the inspected sources
independent-benchmarks. The recorded o3-pro benchmark rows are official vendor evaluations; no independent evaluator row was merged.
Not found in the inspected sources
parameters-billions. OpenAI does not publish parameter counts.
Not found in the inspected sources
AA benchmark rows. No exact-model row in the selected public JSON-LD datasets (some pages only expose N/A or unknown metric summaries).
- Model metadata (retrieved September 8, 2026)Source
- Aider (retrieved September 2, 2026)Source
- Scale AI (retrieved August 26, 2026)Source
- Scale AI (retrieved August 26, 2026)Source
- Scale AI (retrieved August 26, 2026)Source
- Scale AI (retrieved August 26, 2026)Source
- Scale AI (retrieved August 26, 2026)Source
- Scale AI (retrieved August 26, 2026)Source
- OpenAI (retrieved September 8, 2026)Source
- OpenAI (retrieved September 8, 2026)Source
- OpenAI (retrieved September 8, 2026)Source
- Model metadata (retrieved September 8, 2026)Source