OpenAI
gpt-oss-20b (high)
A compact, open-weight language model optimized for low-latency and resource-constrained environments, including local and edge deployments.
Introducing gpt-ossModel Snapshot
TypeLanguage
ReleaseAug 5, 2025
Context131,072
Tagsreasoning, tool-use, implicit-caching
Overall
Rank #312 across 600
14.9
Coding
Rank #202 across 266
20.7
Blended Price
Rank #21 across 379
$0.103/M
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.
Model Details
Runtime
Output Speed187.9 tok/s
First Token0.57s
Max Output131,072
Pricing
Blended$0.103/M
Input$0.070/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 14.9 | #312 |
| Artificial Analysis Coding Index | coding | 20.7 | #202 |
| Artificial Analysis Math Index | math | 89.3 | #30 |
| MMLU-Pro | reasoning | 73.6% | #172 |