Benchmark
Frontiermath Erdos
Math benchmarks measure how well models solve maths problems. Scores are percentages.
All math benchmarksScores from Epoch AI Benchmarking Hub data.
- Models measured
- 16
- Scores recorded
- 16
- Sources
- 1
- IQ weight
- 1.59
Score distribution
- 1.8%
- Mean
- 1.5%
- Median
- 2.6%
- Std dev
- 0%
- 10th percentile
- 4.4%
- 90th percentile
- 0%
- Min
This benchmark has a weight of 1.59 for chat models, measured over 16 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 |
|---|---|---|
| 1 | GPT-6.2 Astramax· Epoch AI Benchmarking Hub data | 10.3% |
| 2 | GPT-6.1 Solmax· Epoch AI Benchmarking Hub data | 4.4% |
| 3 | GPT-6 Astramax· Epoch AI Benchmarking Hub data | 2.9% |
| 4 | Claude Opus 5.5max· Epoch AI Benchmarking Hub data | 2.9% |
| 5 | Gemini 4 Carbonhigh· Epoch AI Benchmarking Hub data | 2.9% |
| 6 | Claude Sonnet 5.5max· Epoch AI Benchmarking Hub data | 2.9% |
| 7 | Gemini 4 Argonhigh· Epoch AI Benchmarking Hub data | 1.5% |
| 8 | GPT-6 Solmax· Epoch AI Benchmarking Hub data | 1.5% |
| 9 | Claude Fable 5max· Epoch AI Benchmarking Hub data | 0% |
| 10 | Claude Fable 5.1max· Epoch AI Benchmarking Hub data | 0% |
| 11 | Claude Opus 5max· Epoch AI Benchmarking Hub data | 0% |
| 12 | Gemini 3.8 Flashhigh· Epoch AI Benchmarking Hub data | 0% |
| 13 | GPT 5.5xhigh· Epoch AI Benchmarking Hub data | 0% |
| 14 | GPT-5.6 Solmax· Epoch AI Benchmarking Hub data | 0% |
| 15 | Grok 4.7xhigh· Epoch AI Benchmarking Hub data | 0% |
| 16 | Kimi K3max· Epoch AI Benchmarking Hub data | 0% |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)