Benchmark
FrontierMath
Math benchmarks measure how well models solve maths problems. Scores are percentages.
- Models measured
- 71
- Scores recorded
- 109
- Sources
- 2
- IQ weight
- 1.73
Score distribution
- 19.5%
- Mean
- 16.4%
- Median
- 18%
- Std dev
- 1.4%
- 10th percentile
- 40.3%
- 90th percentile
- 0%
- Min
This benchmark has a weight of 1.73 for chat models, measured over 71 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 101 | Qwen Max· Epoch AI Benchmarking Hub data | 1% |
| 102 | Grok 2· Epoch AI Benchmarking Hub data | 0.69% |
| 103 | Llama 4 Maverick· Epoch AI Benchmarking Hub data | 0.69% |
| 104 | Mistral Medium 3· Epoch AI Benchmarking Hub data | 0.346% |
| 105 | Claude Haiku 3.5· Epoch AI Benchmarking Hub data | 0.345% |
| 106 | GPT 4o· Epoch AI Benchmarking Hub data | 0.345% |
| 107 | Mistral Large2411· Epoch AI Benchmarking Hub data | 0.345% |
| 108 | gemini-1.5-flash-002· Epoch AI Benchmarking Hub data | 0% |
| 109 | Llama 4 Scout· Epoch AI Benchmarking Hub data | 0% |
Showing 101–109 of 109 results.
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats