Language modelDeprecated

o3-pro

OpenAI

Released: June 10, 2025
Data date: September 8, 2026
Predecessor: o1-pro (Official documentation)
Successor: GPT-5 Pro

Benchmark-Meta-Score: Unavailable
Fewer than eight test series
Price: $20 · $80
Input · Output / 1M tokens
Input: Text, Image
Output: Text

o3-pro differs from o3 in the extra time it spends thinking before answering. OpenAI offered this Pro version in ChatGPT Pro and the API.

GPT-5 Pro later took over the Pro role for especially difficult questions. o3-pro remains a separate checkpoint with extra compute compared with standard o3.

Specifications and access

Specification	Value and source
Weights	ProprietarySource
Access	APISource
Context window	200,000 tokensSource
Knowledge cutoff	June 1, 2024Source
Notes	Reasoning model, parameter count not disclosedSource
API model ID	o3-proSource
Maximum output	100,000 tokensSource
Input	Text, ImageSource
Output	TextSource
Reasoning mode	medium, high, xhighSource
API interfaces	Responses APISource
Tool calling	YesSource
Structured output	YesSource
Release	2025-06-10Source

Benchmark meta-analysis

Overall and area scores

These Gradually indexes place selected published measurements on a 0 to 100 scale. They are not accuracy percentages and do not guarantee results in your application.

Retrieval dates of the sources used 2026-08-26 - 2026-08-26

Overall index

Not enough independent results for a score yet

An overall score needs at least eight test series.

provisional

Published configurations differ within this comparison cohort. Treat the index as provisional.

Test series: 6
Test families: 4 / 65
Sources: 1
Share of the fixed test panel (informative): 7 %

Reasoning

Index 5.7 / 100

provisional

Published configurations differ within this comparison cohort. Treat the index as provisional.

Standard error: ± 2.6
95% interval: 2.1 to 12.8
Test series: 1
Test families: 1 / 7
Sources: 1
Share of the fixed test panel (informative): 14 %

Finance

Index 16.6 / 100

provisional

Published configurations differ within this comparison cohort. Treat the index as provisional.

Standard error: ± 4.6
95% interval: 9.1 to 27.3
Test series: 1
Test families: 1 / 7
Sources: 1
Share of the fixed test panel (informative): 14 %

Legal

Index 21.1 / 100

provisional

Published configurations differ within this comparison cohort. Treat the index as provisional.

Standard error: ± 5.4
95% interval: 12.1 to 33.1
Test series: 1
Test families: 1 / 4
Sources: 1
Share of the fixed test panel (informative): 25 %

Multimodal

Index 8.9 / 100

provisional

Published configurations differ within this comparison cohort. Treat the index as provisional.

Standard error: ± 3.8
95% interval: 3.6 to 18.7
Test series: 1
Test families: 1 / 4
Sources: 1
Share of the fixed test panel (informative): 25 %

Productivity

Index 9.9 / 100

provisional

Published configurations differ within this comparison cohort. Treat the index as provisional.

Standard error: ± 3.7
95% interval: 4.5 to 19.1
Test series: 1
Test families: 1 / 2
Sources: 1
Share of the fixed test panel (informative): 50 %

Education

Index 10.2 / 100

provisional

Published configurations differ within this comparison cohort. Treat the index as provisional.

Standard error: ± 4.3
95% interval: 4.1 to 21.2
Test series: 1
Test families: 1 / 2
Sources: 1
Share of the fixed test panel (informative): 50 %

Documented method · Included test families and measurements

Method version: benchmark-meta-score-v3

The index includes active measurements from reviewed primary sources when at least five models are compared in the same documented comparison slice across dataset, harness, agent, tools, and trial count. Each benchmark series and evaluator contributes one shared setup slice from the newest capture. When one source and series include several explicitly documented reasoning tiers, the highest documented tier (none through max) is selected, never the best result value. The explicit source label “Non-reasoning” is treated as none. Unknown or ambiguous tiers exclude the model from that series. Within each series, percentages and rates are logit-transformed, other units stay unchanged, and all values are then standardized. A one-factor model then estimates one shared strength per model and, per series, how sharply it separates the models. Area scores move away from that strength only as far as the model's own results in the area support. The overall score weights the core areas at 75% and finance, law and health at 25%. It requires at least eight test series from two sources and three areas. The 0 to 100 scale refers to a fixed reference group of 29 language models whose average sits at 50.

Published model-specific parameters can differ. This is not a controlled experiment; comparisons with such differences are marked provisional.

Unmeasured series are not entered as zero. Where a model has no own results in a core area, its overall strength stands in, and the note “estimated without own results in …” names the area. Fewer test series lead to a larger standard error.

The 95% interval follows from the standard error of 200 recalculations with randomly redrawn test families. It describes how precisely the recorded test series determine the value. It is no prediction for future tasks or for later recalculations with other participants.

The source count is not a count of independent experiments.

OECD handbook on composite indicators

All 6 test families and 6 of 6 raw measurements are listed here. The complete calculation for every model is available in the JSON export.

Test family: MultiChallenge
Productivity · Mean rank percentile of the family: 57.1 / 100
Family weight in the fixed test panel (informative): 0 % · Coverage of this test family: 100 %
- Scale AI
  Published configurations differ within this cohort.
  Measurement:
  multichallenge
  Series weight within the test family:
  100 %
  Nominal contribution to the overall panel:
  0 %
  Raw value:
  62.4 %
  Metric:
  rubric pass rate
  Version:
  four multi-turn challenge types
  Participating models:
  8
  Rank percentile within the cohort:
  57.1 %
  Retrieved:
  2026-08-26
  Comparison cohort:
  scale-multichallenge-overall
  Reasoning tier:
  high
  Documented comparison setup
  Publication cohort:
  scale-multichallenge-overall
  Dataset type:
  public
  Attempts:
  pass@1
  Setup and model parameters
  Multi-turn conversations with binary task-specific rubrics.. Attempts: pass@1. Reasoning effort: high
  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: 2026-10-15
Test family: MultiNRC
Reasoning · Mean rank percentile of the family: 45.5 / 100
Family weight in the fixed test panel (informative): 1.53 % · Coverage of this test family: 100 %
- Scale AI
  Published configurations differ within this cohort.
  Measurement:
  multinrc
  Series weight within the test family:
  100 %
  Nominal contribution to the overall panel:
  1.53 %
  Raw value:
  49 %
  Metric:
  accuracy
  Version:
  French, Spanish, and Chinese release
  Participating models:
  12
  Rank percentile within the cohort:
  45.5 %
  Retrieved:
  2026-08-26
  Comparison cohort:
  scale-multinrc-native-languages
  Reasoning tier:
  high
  Documented comparison setup
  Publication cohort:
  scale-multinrc-native-languages
  Dataset type:
  public
  Attempts:
  pass@1
  Setup and model parameters
  Native, non-translated reasoning tasks with automatic evaluation.. Attempts: pass@1. Reasoning effort: high
  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: 2026-10-15
Test family: PRBench Finance
Finance · Mean rank percentile of the family: 66.7 / 100
Family weight in the fixed test panel (informative): 1.19 % · Coverage of this test family: 100 %
- Scale AI
  Published configurations differ within this cohort.
  Measurement:
  prbench-finance
  Series weight within the test family:
  100 %
  Nominal contribution to the overall panel:
  1.19 %
  Raw value:
  49.08 %
  Metric:
  weighted rubric score
  Version:
  full finance set
  Participating models:
  16
  Rank percentile within the cohort:
  66.7 %
  Retrieved:
  2026-08-26
  Comparison cohort:
  scale-prbench-finance-full
  Documented comparison setup
  Publication cohort:
  scale-prbench-finance-full
  Dataset type:
  public
  Attempts:
  pass@1
  Setup and model parameters
  600 finance tasks with task-specific rubrics and o4-mini as judge.. Attempts: pass@1
  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: 2026-10-15
Test family: PRBench Legal
Legal · Mean rank percentile of the family: 73.3 / 100
Family weight in the fixed test panel (informative): 2.08 % · Coverage of this test family: 100 %
- Scale AI
  Published configurations differ within this cohort.
  Measurement:
  prbench-legal
  Series weight within the test family:
  100 %
  Nominal contribution to the overall panel:
  2.08 %
  Raw value:
  49.67 %
  Metric:
  weighted rubric score
  Version:
  full legal set
  Participating models:
  16
  Rank percentile within the cohort:
  73.3 %
  Retrieved:
  2026-08-26
  Comparison cohort:
  scale-prbench-legal-full
  Documented comparison setup
  Publication cohort:
  scale-prbench-legal-full
  Dataset type:
  public
  Attempts:
  pass@1
  Setup and model parameters
  500 legal tasks with task-specific rubrics and o4-mini as judge.. Attempts: pass@1
  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: 2026-10-15
Test family: TutorBench
Education · Mean rank percentile of the family: 66.7 / 100
Family weight in the fixed test panel (informative): 0 % · Coverage of this test family: 100 %
- Scale AI
  Published configurations differ within this cohort.
  Measurement:
  tutorbench
  Series weight within the test family:
  100 %
  Nominal contribution to the overall panel:
  0 %
  Raw value:
  54.62 %
  Metric:
  weighted rubric score
  Version:
  1,490-task release
  Participating models:
  10
  Rank percentile within the cohort:
  66.7 %
  Retrieved:
  2026-08-26
  Comparison cohort:
  scale-tutorbench-overall
  Documented comparison setup
  Publication cohort:
  scale-tutorbench-overall
  Dataset type:
  public
  Attempts:
  pass@1
  Setup and model parameters
  1,490 tasks with weighted rubrics and Claude 4 Sonnet as judge.. Attempts: pass@1
  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: 2026-10-15
Test family: VISTA
Multimodal · Mean rank percentile of the family: 69.2 / 100
Family weight in the fixed test panel (informative): 2.68 % · Coverage of this test family: 100 %
- Scale AI
  Published configurations differ within this cohort.
  Measurement:
  vista
  Series weight within the test family:
  100 %
  Nominal contribution to the overall panel:
  2.68 %
  Raw value:
  51.63 %
  Metric:
  rubric score
  Version:
  758 private prompt-image pairs
  Participating models:
  14
  Rank percentile within the cohort:
  69.2 %
  Retrieved:
  2026-08-26
  Comparison cohort:
  scale-vista-private-overall
  Reasoning tier:
  high
  Documented comparison setup
  Publication cohort:
  scale-vista-private-overall
  Dataset type:
  public
  Attempts:
  pass@1
  Setup and model parameters
  758 single-turn image-text tasks with structured yes-no rubrics.. Attempts: pass@1. Reasoning effort: high
  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: 2026-10-15

Benchmark sources at a glance

Each evaluator measures different capabilities under its own conditions. Test series, composite indices and their components stay separate. The detailed results below retain their scales, configurations and source dates.

Evaluator	Test series	Composite indices	Recorded active measurements
Scale AI Evals	6	0	6

Coverage is not a quality ranking. Overlapping tests and multiple settings do not count as independent experiments. Vendor claims, historical and disputed results are excluded from this overview and remain labelled in the detailed evidence.

Published benchmarks

Aider Polyglot

Overall

225 code-editing tasks from Exercism across C++, Go, Java, JavaScript, Python, and Rust. Aider, the edit format, reasoning budget, and two attempts are part of the result.

1.o3-pro84.9%

2.Gemini 2.5 Pro83.1%

3.o381.3%

4.DeepSeek-R171.4%

higher is betterAs of September 2, 2026Scale: 0% - 100%

Source: Aider

|

gradually.ai

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: 2026-10-15

MultiChallenge

Overall

Multi-turn conversations test memory, instruction retention, versioned editing, and self-coherence. Tasks were selected from shared failures of six older frontier models and may disadvantage those systems.

1.Gemini 3.1 Pro Preview71.37%

2.GPT-5.4 Pro69.23%

3.GPT-563.19%

4.o3-pro62.4%

5.Claude Opus 4.558.97%

6.o356.62%

7.Claude Opus 4.656.02%

8.Claude Sonnet 4.555.32%

higher is betterAs of August 26, 2026Scale: 0% - 100%

Source: Scale AI

|

gradually.ai

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: 2026-10-15

Source: Scale AI

MultiNRC

Overall

Native reasoning tasks in French, Spanish, and Chinese that were not translated from English templates. Three languages counter English-only evaluation, but they do not represent global language coverage.

1.GPT-5 Pro65.2%

2.Gemini 3.1 Pro Preview64.74%

3.GPT-5.4 Pro62.27%

4.GPT-5.458.29%

5.GPT-552.13%

7.Gemini 2.5 Pro45.12%

8.DeepSeek-R127.58%

9.GPT-4.121.23%

10.Llama 4 Maverick8.44%

higher is betterAs of August 26, 2026Scale: 0% - 100%

Source: Scale AI

|

gradually.ai

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: 2026-10-15

Source: Scale AI

PRBench Finance

Overall

600 realistic finance questions with weighted criteria, including a 300-question hard subset. An o4-mini judge scores the responses, so domain correctness and operational reliability remain separate questions.

1.Claude Fable 553.86%

2.Claude Opus 4.653.28%

3.GPT-551.32%

4.GPT-5 Pro51.06%

5.GPT-5.6 Sol50.45%

6.o3-pro49.08%

7.o347.69%

8.Claude Opus 4.546.16%

9.GPT-5.445.63%

10.Claude Sonnet 4.543.79%

11.Gemini 3.1 Pro Preview41.87%

12.o4-mini39.22%

13.Gemini 2.5 Pro38.92%

14.Gemini 2.5 Flash38.41%

15.GPT-4.134.32%

16.Llama 4 Maverick22.36%

higher is betterAs of August 26, 2026Scale: 0% - 100%

Source: Scale AI

|

gradually.ai

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: 2026-10-15

Source: Scale AI

PRBench Legal

Overall

500 realistic legal questions with weighted criteria across jurisdictions and practice areas. The benchmark measures professional response quality but cannot replace legal review or human accountability.

1.Claude Fable 552.56%

2.Claude Opus 4.652.27%

3.GPT-5.6 Sol50.5%

4.GPT-5 Pro49.89%

5.o3-pro49.67%

6.GPT-548.96%

7.o348.57%

8.GPT-5.444.35%

9.Claude Opus 4.544.21%

10.Gemini 3.1 Pro Preview44.02%

11.Gemini 2.5 Pro41.43%

12.Gemini 2.5 Flash41.02%

13.Claude Sonnet 4.540.84%

14.o4-mini38.11%

15.GPT-4.136.48%

16.Llama 4 Maverick24.84%

higher is betterAs of August 26, 2026Scale: 0% - 100%

Source: Scale AI

|

gradually.ai

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: 2026-10-15

Source: Scale AI

TutorBench

Overall

1,490 tasks test adaptive explanations, feedback, and hints across six STEM subjects. A Claude 4 Sonnet judge scores weighted rubrics, so strong results do not prove safe tutoring of real learners.

1.GPT-5.4 Pro56.62%

2.Gemini 2.5 Pro55.65%

3.GPT-555.33%

4.o3-pro54.62%

5.Gemini 3.1 Pro Preview52.99%

6.Gemini 3.1 Flash-Lite51.5%

7.Llama 4 Maverick40.2%

8.GPT-4o36.12%

higher is betterAs of August 26, 2026Scale: 0% - 100%

Source: Scale AI

|

gradually.ai

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: 2026-10-15

Source: Scale AI

VISTA

Overall

758 image-text tasks combine OCR, spatial understanding, object recognition, and open-ended visual reasoning. The dataset is private and uses task-specific rubrics, making independent reproduction difficult.

1.Gemini 2.5 Pro54.63%

2.GPT-5.4 Pro53.89%

3.GPT-5 Pro52.39%

4.o3-pro51.63%

5.GPT-5.450.89%

6.GPT-5 mini50.39%

7.GPT-549.69%

8.GPT-4.145.34%

9.GPT-4.1 mini41.14%

10.Llama 4 Maverick38.33%

11.GPT-4.1 nano26.55%

higher is betterAs of August 26, 2026Scale: 0% - 100%

Source: Scale AI

|

gradually.ai

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: 2026-10-15

Source: Scale AI

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
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
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
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
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
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

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: 2026-10-15
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: 2026-10-15
Comparison methodology: Multi-turn conversations with binary task-specific rubrics.

Source Scale AI

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: 2026-10-15
Comparison methodology: Native, non-translated reasoning tasks with automatic evaluation.

Source Scale AI

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: 2026-10-15
Comparison methodology: 600 finance tasks with task-specific rubrics and o4-mini as judge.

Source Scale AI

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: 2026-10-15
Comparison methodology: 500 legal tasks with task-specific rubrics and o4-mini as judge.

Source Scale AI

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: 2026-10-15
Comparison methodology: 1,490 tasks with weighted rubrics and Claude 4 Sonnet as judge.

Source Scale AI

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: 2026-10-15
Comparison methodology: 758 single-turn image-text tasks with structured yes-no rubrics.

Source Scale AI

Page 1 of 2

Predecessor and successor

Predecessor: o1-pro (Official documentation)
Official documentation
Model lineage evidence
OpenAI announced o3-pro rolling out to all ChatGPT Pro and Team users in the model picker in place of o1-pro, the previous Pro-tier reasoning model; o1-pro has no directory profile.
OpenAI o3-pro rollout announcement (2026-09-19)
Successor: GPT-5 Pro
Model lineage evidence
OpenAI describes GPT-5 pro as replacing OpenAI o3-pro for the most challenging, complex tasks. This records the provider's explicit Pro-tier replacement statement, not the broader GPT-5 model-picker migration.
OpenAI, "Introducing GPT-5" (2026-09-22)

Sources and data date

Type	Evidence and data date
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · Model metadata (retrieved September 8, 2026) · o3-pro API model documentation · Editorial description reviewed October 2, 2026
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · o3-pro API model documentation · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · o3-pro API model documentation · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 7 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources	independent-benchmarks Original wording The recorded o3-pro benchmark rows are official vendor evaluations; no independent evaluator row was merged.
Not found in the inspected sources	parameters-billions Original wording OpenAI does not publish parameter counts.
Not found in the inspected sources	AA benchmark rows Original wording No exact-model row in the selected public JSON-LD datasets (some pages only expose N/A or unknown metric summaries).
Additional source	Aider (retrieved September 2, 2026)
Additional source	Scale AI (retrieved August 26, 2026)
Additional source	Scale AI (retrieved August 26, 2026)
Additional source	Scale AI (retrieved August 26, 2026)
Additional source	Scale AI (retrieved August 26, 2026)
Additional source	Scale AI (retrieved August 26, 2026)
Additional source	Scale AI (retrieved August 26, 2026)
Additional source	OpenAI (retrieved September 8, 2026)
Additional source	OpenAI (retrieved September 8, 2026)
Additional source	OpenAI (retrieved September 8, 2026)
Additional source	Model metadata (retrieved September 8, 2026)
Additional source	Introducing OpenAI o3 and o4-mini · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Ollama: cumulative downloads for the popularity index
Additional source	Replicate: cumulative runs for the popularity index
Additional source	Google Trending Now: limited feed selection for Germany and the US
Additional source	Creative Commons Attribution 4.0
Additional source	OpenAI o3-pro rollout announcement (2026-09-19)
Additional source	OpenAI, "Introducing GPT-5" (2026-09-22)