Benchmark
HMMT25
Math benchmarks measure how well models solve maths problems. Scores are percentages.
All math benchmarksScores from LLM Stats data.
- Models measured
- 23
- Scores recorded
- 25
- Sources
- 1
- IQ weight
- 1.71
Score distribution
- 75.7%
- Mean
- 78.3%
- Median
- 15.9%
- Std dev
- 54.1%
- 10th percentile
- 90.7%
- 90th percentile
- 32.5%
- Min
This benchmark has a weight of 1.71 for chat models, measured over 23 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 | Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 94.6% |
| 2 | Qwen3.5 397B A17B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 92.7% |
| 3 | Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 90.7% |
| 4 | Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 90.3% |
| 5 | Grok 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 90% |
| 6 | Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.8% |
| 7 | Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.2% |
| 8 | Granite 4.2 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.2% |
| 9 | Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.1% |
| 10 | Sarvam 105B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 85.8% |
| 11 | Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 83.9% |
| 12 | Qwen3.5 9B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 82.9% |
| 13 | Granite 4.2 8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.3% |
| 14 | Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 77.4% |
| 15 | Qwen3.5 4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 76.8% |
| 16 | Sarvam-30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 74.2% |
| 17 | Qwen3 Next 80B A3Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.9% |
| 18 | qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 67.6% |
| 19 | Granite 4.2 3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 66.7% |
| 20 | Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 60.6% |
| 21 | Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 57.4% |
| 22 | Qwen3 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 55.4% |
| 23 | Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.1% |
| 24 | qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 50.6% |
| 25 | Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 32.5% |
Data credits: Data by LLM Stats