OpenAI
gpt-oss-20B (low)
gpt-oss-20B (low) 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-ossOperational Metrics
Output Speed249.7 tok/s
First Token0.42s
Blended Price$0.108/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseAug 5, 2025
Context Windown/a
Modalitiesn/a
Strength: Speed
Rank #8 across 293 models.
249.7 tok/s
Strength: Value
Rank #22 across 323 models.
192.6
Strength: TTFT
Rank #21 across 293 models.
0.42s
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 20.8 | #229 |
| Artificial Analysis Coding Index | coding | 14.4 | #249 |
| Artificial Analysis Math Index | math | 62.3 | #113 |
| MMLU-Pro | reasoning | 71.8% | #208 |