Benchmark
Hmmt Feb 2026
Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.
All math benchmarksScores from Hugging Face Official Benchmarks data.
- Models measured
- 19
- Scores recorded
- 19
- Sources
- 1
- IQ weight
- 2.52
Score distribution
- 82.2%
- Mean
- 86.4%
- Median
- 12.7%
- Std dev
- 63.8%
- 10th percentile
- 92.7%
- 90th percentile
- 49.3%
- Min
This benchmark has a weight of 2.52 for chat models, measured over 19 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 | Inkling 2 Small· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 95.8% |
| 2 | DeepSeek V4 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 95.2% |
| 3 | Kimi K2.6· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 92.7% |
| 4 | GLM 5.2· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 92.5% |
| 5 | Inkling Small· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 90.2% |
| 6 | Qwen3.5 397B A17B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 87.9% |
| 7 | Kimi K2.5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 87.1% |
| 8 | Ling 3.0 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 87% |
| 9 | GLM 5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 86.4% |
| 10 | Step 3.5 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 86.4% |
| 11 | Nemotron 3 Super 120B A12B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 84.8% |
| 12 | Qwen3.6 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 84.3% |
| 13 | Qwen3.6 35B A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 83.6% |
| 14 | GLM 5.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 82.6% |
| 15 | Qwen3.5 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 81.1% |
| 16 | Qwen3 30B A3B2507, thinking· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.8% |
| 17 | MiniCPM5-2B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 63.8% |
| 18 | Qwen3-4B-Thinking-2507· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 53% |
| 19 | Ling 2.6 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 49.3% |
Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark