GPT-5.1 benchmark ranking on every AI leaderboard
closed weights · #39 overall, podium score 3.3 · top 10 on 1 of 13 · released Nov 12, 2025
13 of 13 boards
| Rank | Board | Score | |||
|---|---|---|---|---|---|
| 6 |  MultiChallengeChat · as “gpt-5.1-2025-11-13-thinking” | Chat | 63.4% | 29 | |
| 14 |  Search ArenaAgents and tools · as “gpt-5.1-search” | Agents and tools | 1,199 | 33 | |
| 16 | HLEReasoning · as “gpt-5.1-thinking” | Reasoning | 23.7% | 42 | |
| 32 | MCP AtlasAgents and tools · as “gpt-5.1 (high)” | Agents and tools | 50.1% | 34 | |
| 37 | Document ArenaVision · as “gpt-5.1” | Vision | 1,403 | 38 | |
| 38 | Vision ArenaVision · as “gpt-5.1-high” | Vision | 1,250 | 100 | |
| 40 |  ARC-AGI-2Reasoning · as “GPT-5.1 (Thinking, High)” | Reasoning | 17.6% | 78 | |
| 45 |  GPQA DiamondReasoning · as “gpt-5.1-2025-11-13_high” | Reasoning | 87.6% | 100 | |
| 51 | Epoch ECIReasoning · as “GPT-5.1” | Reasoning | 149.7 | 100 | |
| 53 | Text ArenaChat · as “gpt-5.1-high” | Chat | 1,455 | 100 | |
| 69 | WebDev ArenaCoding · as “gpt-5.1-medium” | Coding | 1,392 | 100 | |
| 14 |  SWE-bench VerifiedCoding · stale since 2026-02-26 · as “GPT 5.1 (2025-11-13) (medium)” | Coding | 66.0% | 39 | |
| 24 |  MMLU-ProReasoning · stale since 2026-03-11 · as “GPT-5.1” | Reasoning | 86.4% | 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.