OpenAI
gpt-oss-120b (high)
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
Introducing gpt-ossModel Snapshot
ReleaseAug 5, 2025
Context131,072
Overall
Rank #184 across 566
23.8
Coding
Rank #134 across 222
30.4
Blended Price
Rank #69 across 371
$0.262/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 Speed231.3 tok/s
First Token0.56s
Max Output131,072
Pricing
Blended$0.262/M
Input$0.150/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 23.8 | #184 |
| Artificial Analysis Coding Index | coding | 30.4 | #134 |
| Artificial Analysis Math Index | math | 93.4 | #15 |
| MMLU-Pro | reasoning | 80.8% | #103 |