Benchmark
U-MATH multivariable_calculus accuracy
Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.
- Models measured
- 30
- Scores recorded
- 90
- Sources
- 1
- IQ weight
- 1.46
Score distribution
- 41.2%
- Mean
- 40.7%
- Median
- 24%
- Std dev
- 10.7%
- 10th percentile
- 78.7%
- 90th percentile
- 0%
- Min
This benchmark has a weight of 1.46 for chat models, measured over 30 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 |
|---|---|---|
| 51 | GPT-4o minimultivariable_calculus, text, gpt-4o-2024-08-06· U-MATH and mu-MATH | 37.3% |
| 52 | Qwen2.5 7B Instructmultivariable_calculus, text, gpt-4o-2024-08-06· U-MATH and mu-MATH | 36.7% |
| 53 | Nvidia Llama 3.1 Nemotron 70B Instructmultivariable_calculus, all, gpt-4o-2024-08-06· U-MATH and mu-MATH | 36.5% |
| 54 | Claude 3.5 Sonnetmultivariable_calculus, all, gpt-4o-2024-08-06· U-MATH and mu-MATH | 34.3% |
| 55 | Claude 3.5 Sonnetmultivariable_calculus, text, gpt-4o-2024-08-06· U-MATH and mu-MATH | 33.3% |
| 56 | QwQ 32B Previewmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 32.1% |
| 57 | Qwen2-VL (72B) Instructmultivariable_calculus, text, gpt-4o-2024-08-06· U-MATH and mu-MATH | 32% |
| 58 | Qwen2-VL (72B) Instructmultivariable_calculus, all, gpt-4o-2024-08-06· U-MATH and mu-MATH | 31.5% |
| 59 | Qwen2.5 7B Instructmultivariable_calculus, all, gpt-4o-2024-08-06· U-MATH and mu-MATH | 31.5% |
| 60 | Llama 3.2 90B Vision Instructmultivariable_calculus, text, gpt-4o-2024-08-06· U-MATH and mu-MATH | 30% |
| 61 | Phi 4multivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 28.6% |
| 62 | Qwen2-VL (72B) Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 28.6% |
| 63 | Llama 3.2 90B Vision Instructmultivariable_calculus, all, gpt-4o-2024-08-06· U-MATH and mu-MATH | 27% |
| 64 | Llama 3.1 70B Instructmultivariable_calculus, text, gpt-4o-2024-08-06· U-MATH and mu-MATH | 26% |
| 65 | Llama 3.1 8B Instructmultivariable_calculus, text, gpt-4o-2024-08-06· U-MATH and mu-MATH | 23.3% |
| 66 | Llama 3.1 70B Instructmultivariable_calculus, all, gpt-4o-2024-08-06· U-MATH and mu-MATH | 23% |
| 67 | Qwen2.5 Math 72B Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 21.4% |
| 68 | Llama 3.1 8B Instructmultivariable_calculus, all, gpt-4o-2024-08-06· U-MATH and mu-MATH | 20.2% |
| 69 | Qwen2 VL 7b Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 17.9% |
| 70 | Qwen2.5 32B Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 17.9% |
| 71 | Qwen2 VL 7b Instructmultivariable_calculus, all, gpt-4o-2024-08-06· U-MATH and mu-MATH | 14.6% |
| 72 | Mistral Large Instruct 2411multivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 14.3% |
| 73 | Nvidia Llama 3.1 Nemotron 70B Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 14.3% |
| 74 | Qwen2.5 72B Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 14.3% |
| 75 | Qwen2 VL 7b Instructmultivariable_calculus, text, gpt-4o-2024-08-06· U-MATH and mu-MATH | 14% |
| 76 | LFM-7bmultivariable_calculus, text, gpt-4o-2024-08-06· U-MATH and mu-MATH | 13.3% |
| 77 | Llama 3.2 11B Vision Instructmultivariable_calculus, text, gpt-4o-2024-08-06· U-MATH and mu-MATH | 13.3% |
| 78 | LFM-7bmultivariable_calculus, all, gpt-4o-2024-08-06· U-MATH and mu-MATH | 12.9% |
| 79 | Llama 3.2 11B Vision Instructmultivariable_calculus, all, gpt-4o-2024-08-06· U-MATH and mu-MATH | 11.2% |
| 80 | LFM-7bmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 10.7% |
| 81 | Llama 3.2 90B Vision Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 10.7% |
| 82 | Llama 3.3 70B Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 10.7% |
| 83 | Qwen2.5 Math 7B Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 10.7% |
| 84 | Llama 3.1 70B Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 7.1% |
| 85 | Pixtral 12Bmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 7.1% |
| 86 | Pixtral 12Bmultivariable_calculus, all, gpt-4o-2024-08-06· U-MATH and mu-MATH | 6.7% |
| 87 | Pixtral 12Bmultivariable_calculus, text, gpt-4o-2024-08-06· U-MATH and mu-MATH | 6.7% |
| 88 | Llama 3.1 8B Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 3.6% |
| 89 | Qwen2.5 7B Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 3.6% |
| 90 | Llama 3.2 11B Vision Instructmultivariable_calculus, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH | 0% |
Showing 51–90 of 90 results.
Data credits: Toloka, U-MATH and mu-MATH public leaderboard. MIT Space; generated solution outputs retain underlying model terms and are not ingested. (licence)