GPT 4.1 benchmark ranking on every AI leaderboard
closed weights · top 10 on 0 of 9 · released Apr 14, 2025
9 of 9 boards
| Rank | Board | Score | |||
|---|---|---|---|---|---|
| 17 |  BFCLAgents and tools · as “GPT-4.1-2025-04-14 (FC)” | Agents and tools | 54.0% | 81 | |
| 28 |  MultiChallengeChat · as “gpt-4.1” | Chat | 39.4% | 29 | |
| 36 | HLEReasoning · as “GPT-4.1” | Reasoning | 5.4% | 42 | |
| 61 |  Vision ArenaVision · as “gpt-4.1-2025-04-14” | Vision | 1,214 | 100 | |
| 68 |  ARC-AGI-2Reasoning · as “GPT-4.1” | Reasoning | 0.4% | 78 | |
| 97 |  GPQA DiamondReasoning · as “gpt-4.1-2025-04-14” | Reasoning | 66.9% | 100 | |
| 25 |  Aider PolyglotCoding · stale since 2025-10-03 · as “gpt-4.1” | Coding | 52.4% | 50 | |
| 30 |  SWE-bench VerifiedCoding · stale since 2026-02-26 · as “GPT 4.1 (2025-04-14)” | Coding | 39.6% | 39 | |
| 52 |  MMLU-ProReasoning · stale since 2026-03-11 · as “GPT-4.1” | Reasoning | 81.8% | 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.