o3 benchmark ranking on every AI leaderboard
closed weights · #44 overall, podium score 2.7 · top 10 on 2 of 13 · released Apr 16, 2025
13 of 13 boards
| Rank | Board | Score | |||
|---|---|---|---|---|---|
| 7 |  BFCLAgents and tools · as “o3-2025-04-16 (Prompt)” | Agents and tools | 63.0% | 81 | |
| 16 |  MultiChallengeChat · as “o3-2025-04-16-reasoning-high” | Chat | 56.6% | 29 | |
| 18 | HLEReasoning · as “o3 (high) (April 2025)” | Reasoning | 20.3% | 42 | |
| 26 |  Search ArenaAgents and tools · as “o3-search” | Agents and tools | 1,144 | 33 | |
| 47 |  ARC-AGI-2Reasoning · as “o3 (High)” | Reasoning | 6.5% | 78 | |
| 58 | Vision ArenaVision · as “o3-2025-04-16” | Vision | 1,215 | 100 | |
| 59 |  AA IntelligenceReasoning · as “o3” | Reasoning | 20.2 | 100 | |
| 62 |  Epoch ECIReasoning · as “o3” | Reasoning | 146.9 | 100 | |
| 70 | GPQA DiamondReasoning · as “o3-2025-04-16_high” | Reasoning | 81.8% | 100 | |
| 80 | Text ArenaChat · as “o3-2025-04-16” | Chat | 1,432 | 100 | |
| 4 |  Aider PolyglotCoding · stale since 2025-10-03 · as “o3 (high)” | Coding | 81.3% | 50 | |
| 21 |  SWE-bench VerifiedCoding · stale since 2026-02-26 · as “o3 (2025-04-16)” | Coding | 58.4% | 39 | |
| 33 |  MMLU-ProReasoning · stale since 2026-03-11 · as “GPT-o3-high” | Reasoning | 85.0% | 100 |
Category ranks and more models
Sources: each leaderboard's own published results page, captured every day at 04:30 UTC. Scores exactly as each board published them; we run no evaluations. Logos via logo.dev; trademarks belong to their owners.