OpenAIOpenAI o-series (o3)
OpenAI o3-pro
OpenAI · OpenAI o-series (o3). Released Jun 10, 2025.
OpenAI o3-pro is a model from OpenAI in the OpenAI o-series (o3) family, released Jun 10, 2025. evals.report tracks 8 reported OpenAI o3-pro benchmark scores across GPQA Diamond, Artificial Analysis Intelligence Index, Epoch Capabilities Index, Aider Polyglot, MultiChallenge, MASK (Model Alignment between Statements and Knowledge), Vectara Hallucination Leaderboard, MultiNRC — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.
8 results
Benchmark results 8
Compare this model| Benchmark | Category | Score | Metric | Status | Date | |
|---|---|---|---|---|---|---|
| GPQA Diamond | Reasoning | 84% | accuracy | Unverified | Jun 10, 2025 | Details |
| Artificial Analysis Intelligence Index | Reasoning | 40.7 | Index | Unverified | Jun 10, 2025 | Details |
| Epoch Capabilities Index | Reasoning | 148.1 | Index | Official | Jun 10, 2025 | Details |
| Aider Polyglot | Coding | 84.9% | % correct | Official | Jun 10, 2025 | Details |
| MultiChallenge | Reasoning | 62.40% | accuracy | Verified | Jun 10, 2025 | Details |
| MASK (Model Alignment between Statements and Knowledge) | Other | 82.50 | Honesty score | Verified | Jun 10, 2025 | Details |
| Vectara Hallucination Leaderboard | Other | 23.3% | Hallucination Rate | Official | Jun 10, 2025 | Details |
| MultiNRC | Reasoning | 49.00% | accuracy | Official | Jun 10, 2025 | Details |