GPT-5.1 Instant
GPT-5.1 Instant.
9
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
OpenAI Nov 2025
GPT-5.1 Instant
Closed weights Flagship
No Epoch Capabilities Index score yet
- Humanity's Last Exam 6.80% #37 /47
- MultiChallenge 51.2% #29 /42
- VISTA 34.9% #41 /54
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 | |
|---|---|---|---|---|
| BullshitBench | 36.4% | #41 of 107 | Official leaderboard | |
| BullshitBench V2 | 45% | #59 of 129 | Official leaderboard | |
| MultiChallenge | 51.2% | #29 of 42 | Official leaderboard | |
| Humanity's Last Exam | 6.80% | #37 of 47 | Official leaderboard | |
| MultiNRC | 18.3% | #31 of 38 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LLM Chess | -131 | #82 of 123 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| VISTA | 34.9% | #41 of 54 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| FORTRESS | 30.4% | #47 of 73 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| TutorBench | 49.1% | #17 of 20 | Official leaderboard |