Rankings / OpenAI
O3 Pro (2025-06-10)
released 2025-06-10
BenchAtlas Index
as of 2026-07-14
Benchmark evidence
27 results
external indices
| ECI | medium effort | 147.9 points | independent | Epoch AI Benchmarking Hub |
| ECI | high effort | 147.9 points | independent | Epoch AI Benchmarking Hub |
| ECI | low effort | 147.9 points | independent | Epoch AI Benchmarking Hub |
reasoning math
| ARC-AGI-1older version split=public_eval · model_type=CoT + Synthesis | high effort | 63.3 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT + Synthesis | high effort | 59.3 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=public_eval · model_type=CoT + Synthesis | medium effort | 58.1 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT + Synthesis | medium effort | 57.0 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=public_eval · model_type=CoT + Synthesis | low effort | 50.9 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT + Synthesis | low effort | 44.3 % | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT + Synthesis | high effort | 9.1 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT + Synthesis | high effort | 7.6 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT + Synthesis | medium effort | 5.2 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT + Synthesis | high effort | 4.9 % | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT + Synthesis | medium effort | 4.7 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT + Synthesis | high effort | 4.2 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=public_eval · model_type=CoT + Synthesis | high effort | 3.9 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT + Synthesis | high effort | 3.9 % | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT + Synthesis | medium effort | 3.5 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT + Synthesis | medium effort | 3.2 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=public_eval · model_type=CoT + Synthesis | medium effort | 2.5 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT + Synthesis | low effort | 2.5 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT + Synthesis | low effort | 2.2 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT + Synthesis | low effort | 2.0 % | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT + Synthesis | low effort | 1.9 % | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT + Synthesis | medium effort | 1.9 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT + Synthesis | low effort | 1.6 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=public_eval · model_type=CoT + Synthesis | low effort | 1.5 usd_per_task | independent | ARC Prize Leaderboard |
