OpenAI
gpt-oss-120B (high) is part of OpenAI's gpt-oss open-weight model family, intended for developers who need strong local or self-hosted language-model capability. The local profile is useful for checking how this deployment-friendly model compares with hosted frontier systems on quality, throughput, and pricing assumptions.
Introducing gpt-ossQueryable facts extracted from the upstream model payload.
Rank #7 across 343 models.
Rank #15 across 269 models.
Rank #18 across 293 models.
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 33.3 | #117 |
| Artificial Analysis Coding Index | coding | 28.6 | #125 |
| Artificial Analysis Math Index | math | 93.4 | #15 |
| MMLU-Pro | reasoning | 80.8% | #100 |
| reasoning |
| 78.2% |
| #120 |
| Humanity's Last Exam | reasoning | 18.5% | #77 |
| LiveCodeBench | coding | 87.8% | #7 |
| SciCode | coding, reasoning | 38.9% | #119 |
| Output Speed | speed | 212.3 tok/s | #18 |
| Time to First Token | speed | 0.49s | #42 |
| Blended Price | cost | $0.263/M | #70 |
| Input Price | cost | $0.150/M | #66 |
| Output Price | cost | $0.600/M | #82 |
| Value Index | cost, overall | 126.6 | #33 |