Model family
GPT (OpenAI) OpenAI
OpenAI’s flagship language models used in ChatGPT and the API.
Published scores mapped to this family
| Source | Benchmark | Published id | Score | Rank | As of |
|---|---|---|---|---|---|
| Hugging Face | MMLU-Pro | openai/gpt-oss-120b | 80.8 | 38 | Oct 7, 2026, 8:57 AM UTC |
| HELM | HELM Capabilities | openai_gpt-5-mini-2025-08-07 | 81.9 | 1 | Oct 7, 2026, 8:57 AM UTC |
| HELM | HELM Capabilities | openai_o4-mini-2025-04-16 | 81.2 | 2 | Oct 7, 2026, 8:57 AM UTC |
| HELM | HELM Capabilities | openai_o3-2025-04-16 | 81.1 | 3 | Oct 7, 2026, 8:57 AM UTC |
| HELM | HELM Capabilities | openai_gpt-5-2025-08-07 | 80.7 | 4 | Oct 7, 2026, 8:57 AM UTC |
| HELM | HELM Capabilities | openai_gpt-oss-120b | 77.0 | 9 | Oct 7, 2026, 8:57 AM UTC |
| HELM | HELM Capabilities | openai_gpt-5-nano-2025-08-07 | 74.8 | 14 | Oct 7, 2026, 8:57 AM UTC |
| HELM | HELM Capabilities | openai_gpt-4.1-2025-04-14 | 72.7 | 18 | Oct 7, 2026, 8:57 AM UTC |
| HELM | HELM Capabilities | openai_gpt-4.1-mini-2025-04-14 | 72.6 | 20 | Oct 7, 2026, 8:57 AM UTC |
| HELM | HELM Capabilities | openai_gpt-oss-20b | 67.4 | 29 | Oct 7, 2026, 8:57 AM UTC |
| HELM | HELM Capabilities | openai_gpt-5.1-2025-11-13 | 65.6 | 33 | Oct 7, 2026, 8:57 AM UTC |
| HELM | HELM Capabilities | openai_gpt-4o-2024-11-20 | 63.4 | 38 | Oct 7, 2026, 8:57 AM UTC |