GPT 4o benchmark ranking on every AI leaderboard
closed weights · top 10 on 0 of 8 · released Nov 20, 2024
| Rank | Board | Score | |||
|---|---|---|---|---|---|
| 33 |  Search ArenaAgents and tools · as “api-gpt-4o-search” | Agents and tools | 1,006 | 33 | |
| 42 |  HLEReasoning · as “GPT-4o (November 2024)” | Reasoning | 2.7% | 42 | |
| 45 | Vision ArenaVision · as “chatgpt-4o-latest-20250326” | Vision | 1,240 | 100 | |
| 65 | Text ArenaChat · as “chatgpt-4o-latest-20250326” | Chat | 1,443 | 100 | |
| 70 |  ARC-AGI-2Reasoning · as “GPT-4o” | Reasoning | 0.0% | 78 | |
| 28 |  Aider PolyglotCoding · stale since 2025-10-03 · as “chatgpt-4o-latest (2025-03-29)” | Coding | 45.3% | 50 | |
| 35 |  SWE-bench VerifiedCoding · stale since 2026-02-26 · as “GPT 4o (2024-11-20)” | Coding | 21.6% | 39 | |
| 72 |  MMLU-ProReasoning · stale since 2026-03-11 · as “GPT-4o (2024-11-20)” | Reasoning | 77.9% | 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.