Benchmark
We-Math
Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.
- Models measured
- 2
- Scores recorded
- 3
- Sources
- 2
- IQ weight
- No weight published
Score distribution
- 88.6%
- Mean
- 89%
- Median
- 0.519%
- Std dev
- 87.9%
- 10th percentile
- 89%
- 90th percentile
- 87.9%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89% |
| 2 | Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 89% |
| 3 | Qwen3.5 397B A17BQwen3.5 release/model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 87.9% |
Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats