GPT-5.1 ChatGPT: benchmark results
Provider: OpenAI. Released 2025-11-12. Access: API.
Unified ELO 1640 ± 1, rank #149 of 1392 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI Chess Leaderboard (Continuation) | 1363 | Elo | 92.6 |
| AI Chess Leaderboard (Reasoning) | 837 | Elo | 68.7 |
| Bullshit Benchmark | 36.4 | BS Detection Rate (%) | 67 |
| Chess Bench LLM | 514 | Lichess Rating | 63.2 |
| SvelteBench | 83.3 | Average pass@1 (%) | 33.1 |
| LLM Chess (Saplin) | -130.7 | ELO | 31.1 |
| SpeechMap Compliance | 40.8 | % Requests Completed | 19 |
Interactive version: theaggregate.ai/model?slug=gpt-5-1-chatgpt · How It Works · Data refreshed daily, snapshot 2026-09-05.