Benchmark
HMMT Feb 25
Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.
- Models measured
- 11
- Scores recorded
- 15
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 95.4%
- Mean
- 94.8%
- Median
- 4.1%
- Std dev
- 90.7%
- 10th percentile
- 100%
- 90th percentile
- 84.4%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 Prono tools · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 100% |
| 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. | 100% |
| 3 | GPT 5.2no tools · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 99.4% |
| 4 | 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. | 99.2% |
| 5 | 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. | 98.7% |
| 6 | 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. | 98.4% |
| 7 | 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. | 96.7% |
| 8 | 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. | 94.8% |
| 9 | Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · with tools· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 94.7% |
| 10 | Nemotron 3 Super 120B A12Bofficial blog Figure 3 · rounded · tool setting not labeled· Reported by NVIDIA Developer· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 94.7% |
| 11 | 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. | 93.8% |
| 12 | Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · no tools· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 93.7% |
| 13 | 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. | 92.5% |
| 14 | 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. | 90.7% |
| 15 | MiMo V2 FlashMiMo-V2-Flash final evaluation · February 2025· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 84.4% |