Benchmark
HMMT Nov 25
Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.
- Models measured
- 12
- Scores recorded
- 14
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 90.7%
- Mean
- 94%
- Median
- 9.5%
- Std dev
- 84.4%
- 10th percentile
- 97.8%
- 90th percentile
- 59%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Step 3.5 FlashStep 3.5 technical report · Tables 12–13 · Python tool· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 98% |
| 2 | Step 3.5 FlashStep 3.5 technical report · Table 5 · PaCoRe· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 97.8% |
| 3 | GLM 5GLM-5 official release table· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 96.9% |
| 4 | 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. | 94.6% |
| 5 | DeepSeek V3.2 SpecialeSpeciale high-compute reasoning · temperature 1.0 · 128K context · pass@1· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 94.4% |
| 6 | GLM 5.2GPT-5.5 medium judge· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 94.4% |
| 7 | GLM 5.1GLM-5.1 official release table· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 94% |
| 8 | Step 3.5 FlashStep 3.5 Flash official headline table · vanilla· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 94% |
| 9 | 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. | 92.7% |
| 10 | Qwen3.6 27BQwen 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. | 90.7% |
| 11 | DeepSeek V3.2Thinking mode · temperature 1.0 · 128K context · custom step-by-step / boxed-answer prompt· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 90.2% |
| 12 | Qwen3.6 FlashQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 89.1% |
| 13 | Qwen3.5 Omni PlusQwen3.5-Omni release · no-thinking setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 84.4% |
| 14 | Qwen3.5 Omni FlashQwen3.5-Omni release · no-thinking setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 59% |