Benchmark
TheoremQA
Math benchmarks measure how well models solve maths problems. Scores are percentages.
All math benchmarksScores from LLM Stats data.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 2.20
Score distribution
- 39%
- Mean
- 43.1%
- Median
- 7.1%
- Std dev
- 34%
- 10th percentile
- 44.4%
- 90th percentile
- 25.3%
- Min
This benchmark has a weight of 2.20 for chat models, measured over 6 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 | Qwen2 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 44.4% |
| 2 | Qwen2.5 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 44.1% |
| 3 | Qwen 2.5 Coder 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 43.1% |
| 4 | Qwen 2.5 14B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 43% |
| 5 | Qwen2.5 Coder 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 34% |
| 6 | Qwen2 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 25.3% |
Data credits: Data by LLM Stats