GPT-5.4 nano
Announced on openai.com
Benchmark results
| Benchmark | Score | Source check |
|---|---|---|
| Humanity's Last ExamNo tools · xhigh effort | 24.3% | CheckedA person checked this number against its source on 26 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| Humanity's Last ExamWith tools · xhigh effort; tools not named | 37.7% | CheckedA person checked this number against its source on 26 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| SWE-bench Proxhigh effort | 52.4% | CheckedA person checked this number against its source on 26 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| GPQA Diamondxhigh effort | 82.8% | CheckedA person checked this number against its source on 26 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| Terminal-Bench 2.0xhigh effort | 46.3% | CheckedA person checked this number against its source on 26 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| OSWorld-Verifiedxhigh effort | 39.0% | CheckedA person checked this number against its source on 26 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
Sources
Reported by OpenAI
- Introducing GPT-5.4 mini and nanoopenai.com · 17 Mar 2026
Our capture of the source 
Our capture of the source