o1-mini
o1-mini is a cost-efficient language model developed by OpenAI, designed for advanced reasoning tasks while minimizing computational resources.
Benchmark results
| Benchmark | Score | Tags | Source |
|---|---|---|---|
| Cybersecurity CTFs | 28.7% | self-reported llm-stats | link → |
| GPQA | 60.0% | self-reported llm-stats | link → |
| HumanEval | 92.4% | self-reported llm-stats | link → |
| MATH-500 | 90.0% | self-reported llm-stats | link → |
| MMLU | 85.2% | self-reported llm-stats | link → |
| SuperGLUE | 75.0% | self-reported llm-stats | link → |