o3-pro
o3-pro ranks first on Fiction.LiveBench.
OpenAI Released 10 Jun 2025
21
Benchmarks with a score
1
Ranked first, out of five or more models
2
In the top three
OpenAI Jun 2025
o3-pro
Closed weights
147.4
#73 of 271
Epoch Capabilities Index
- MultiChallenge 62.4% #14 /35
- PRBench 49.7% #11 /44
- LMCA 38.5% #56 /139
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Fiction.LiveBench | 97.2% | #1 of 57 | Epoch AI | |
| Lech Mazur Creative Writing | 8.44 | #4 of 44 | Epoch AI | |
| MultiNRC | 49% | #10 of 38 | Official leaderboard | |
| LLM Confabulation Leaderboard | 14.2% | #18 of 58 | Official leaderboard | |
| MultiChallenge | 62.4% | #14 of 35 | Official leaderboard | |
| Vectara Hallucination Leaderboard (2025 dataset) | 23.3% | #102 of 104 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIME 2024 | 93% | #8 of 87 | Model card | |
| GPQA Diamond | 84% | #82 of 284 | Model card | |
| DTBench | 78.2% | #65 of 178 | Official leaderboard | |
| ARC-AGI | 59.3% | #59 of 92 | Official leaderboard | |
| ARC-AGI-2 | 4.86% | #66 of 95 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Aider Polyglot | 84.9% | #2 of 54 | Epoch AI | |
| Codeforces rating | 2,748 | #6 of 41 | Model card | |
| WeirdML | 58.2% | #36 of 112 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MCP Atlas | 44.5% | #33 of 34 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PRBench | 49.7% | #11 of 44 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| VISTA | 51.6% | #6 of 54 | Official leaderboard | |
| ClockBench | 14.4% | #24 of 37 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ACCoRD | 73.8 | #29 of 150 | Official leaderboard | |
| Conceptual Reasoning Index | 53.5 | #56 of 149 | Official leaderboard | |
| LMCA | 38.5% | #56 of 139 | Epoch AI |
OpenAI's models over time
OpenAI's models in color, against every other model on the Epoch Capabilities Index, by release date.
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.