Benchmark
Beyond AIME
Math benchmarks measure how well models solve maths problems. Scores are percentages.
All math benchmarksScores from LLM Stats data.
- Models measured
- 7
- Scores recorded
- 7
- Sources
- 1
- IQ weight
- 1.05
Score distribution
- 73.6%
- Mean
- 69.1%
- Median
- 10.1%
- Std dev
- 66.9%
- 10th percentile
- 87%
- 90th percentile
- 58.3%
- Min
This benchmark has a weight of 1.05 for chat models, measured over 7 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 | Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 88% |
| 2 | Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 87% |
| 3 | Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77% |
| 4 | Sarvam 105B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69.1% |
| 5 | Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69% |
| 6 | Mistral Medium 3.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 66.9% |
| 7 | Sarvam-30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 58.3% |
Data credits: Data by LLM Stats