Language Open (Restricted)
- Params
- 116.8B
- Context
- —
- Released
- Aug 2025
🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// COMPARISON
gpt-oss-120b
A head-to-head benchmark comparison of gpt-oss-120b across 16 evaluations.
The models
Benchmark comparison
| Benchmark | gpt-oss-120b |
|---|---|
| agentic | |
| TAU-bench Airline | 49.2% |
| TAU-bench Retail | 67.8% |
| code | |
| Aider Polyglot | 44.4% |
| Codeforces Elo | 2,622 |
| LiveCodeBench v5 | 74.53% |
| SWE-bench Verified | 62.4% |
| general | |
| MMLU | 90% |
| MMMLU | 81.3% |
| math | |
| AIME 2024 | 96.6% |
| AIME 2025 | 97.9% |
| HMMT February 2025 | 81.88% |
| Omni-MATH-HARD | 57.76% |
| reasoning | |
| GPQA Diamond | 80.9% |
| Humanity's Last Exam | 19% |
| safety | |
| HealthBench | 57.6% |
| HealthBench Hard | 30% |
Best result per row highlighted in cyan. Each benchmark links to its definition and sources; each model links to its full scorecard.
Frequently asked questions
Which of these models is best for coding? ▶
gpt-oss-120b has the strongest result on Aider Polyglot among the models compared here. See the code-category rows in the table for the full picture.
How many benchmarks are compared? ▶
This comparison covers 16 benchmarks on which at least one of the selected models has a published score.
Where do the benchmark scores come from? ▶
Scores are aggregated from official model cards, technical reports and standard public evaluations, and link back to each benchmark's source. They are updated as new results are published.
Explore further
Build a different comparison
Models (0 selected)
Benchmarks (auto)
Select at least two models.