gpt-oss-120b
openai/gpt-oss-120b
tool_use
Benchmark Results
Compare with other models →knowledge
| Benchmark | Score | |
|---|---|---|
MMLUlocal | 78.5% |
reasoning
| Benchmark | Score | |
|---|---|---|
GSM8Klocal | 85.2% | |
ARC-Challengelocal | 75.4% |
coding
| Benchmark | Score | |
|---|---|---|
HumanEvallocal | 72.0% |
language
| Benchmark | Score | |
|---|---|---|
HellaSwaglocal | 82.3% |
safety
| Benchmark | Score | |
|---|---|---|
TruthfulQAlocal | 65.8% |