GPT-5.1-Codex
GPT-5.1-Codex.
25
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
OpenAI Nov 2025
GPT-5.1-Codex
Closed weights
No Epoch Capabilities Index score yet
- Terminal-Bench 2.0 57.8% #13 /43
- APEX-SWE 29% #56 /65
- Vibe Code Bench v1 13.1% #10 /17
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Wer wird Millionär? LLM Benchmark | 291667.0 | #8 of 77 | Official leaderboard | |
| BullshitBench | 29.1% | #50 of 107 | Official leaderboard | |
| BullshitBench V2 | 32% | #74 of 129 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SWE-bench Verified | 66% | #20 of 60 | Official leaderboard | |
| FeatureBench | 60.2% | #6 of 16 | Official leaderboard | |
| FeatureBench Lite | 60.2% | #6 of 16 | Official leaderboard | |
| ALE-Bench | 1,528 | #54 of 126 | Official leaderboard | |
| DesignArena UI Component | 1,228 | #61 of 139 | Official leaderboard | |
| DesignArena Data Visualization | 1,211 | #60 of 118 | Official leaderboard | |
| Vibe Code Bench v1 | 13.1% | #10 of 17 | Official leaderboard | |
| DesignArena Game Dev | 1,128 | #94 of 143 | Official leaderboard | |
| DesignArena Website | 1,155 | #100 of 151 | Official leaderboard | |
| DesignArena Code | 1,143 | #98 of 143 | Official leaderboard | |
| WebDev Arena | 1,336 | #86 of 105 | arena.ai, via Epoch AI | |
| Vibe Code Bench | 13.1% | #99 of 120 | Official leaderboard | |
| Code Arena | 1,338 | #106 of 128 | Official leaderboard | |
| IOI (Vals) | 3.67% | #46 of 55 | Official leaderboard | |
| APEX-SWE | 29% | #56 of 65 | Official leaderboard | |
| DesignArena Agentic Overall | 1,027 | #66 of 74 | Official leaderboard | |
| DesignArena Frontend Web App | 1,000 | #53 of 53 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 32 | #28 of 188 | Official leaderboard | |
| Terminal-Bench 2.0 | 57.8% | #13 of 43 | Official leaderboard | |
| LLM Chess | 504 | #41 of 123 | Official leaderboard | |
| WeaveBench | 1.80% | #7 of 9 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| UK AISI and CAISI simulated enterprise network range | 9.80 | #4 of 6 | Official leaderboard |