OpenAI
gpt-oss-20B (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-ossRank #326 across 526
Rank #226 across 436
Rank #19 across 357
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 | 14.9 | #326 |
| Artificial Analysis Coding Index | coding | 18.5 | #226 |
| Artificial Analysis Math Index | math | 89.3 | #30 |
| MMLU-Pro | reasoning | 74.8% | #182 |
| reasoning |
| 68.8% |
| #230 |
| Humanity's Last Exam | reasoning | 9.8% | #172 |
| LiveCodeBench | coding | 77.7% | #37 |
| SciCode | coding, reasoning | 34.4% | #218 |
| Output Speed | speed | 240 tok/s | #16 |
| Time to First Token | speed | 0.48s | #33 |
| Blended Price | cost | $0.088/M | #19 |
| Input Price | cost | $0.050/M | #19 |
| Output Price | cost | $0.200/M | #26 |
| Value Index | cost, overall | 169.3 | #27 |