Skip to content

Benchmark

U-MATH algebra 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
2.19

Score distribution

59.7%
Mean
72.2%
Median
31%
Std dev
10%
10th percentile
92%
90th percentile
0%
Min
0%99.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.19 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

#ModelScore
1o3 Minialgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH99.3%
2o1algebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH97.3%
3O1 Minialgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH97.3%
4DeepSeek R1algebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH96.7%
5DeepSeek V3algebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH96%
6Gemini 2.0 Flash Experimentalalgebra, text, gpt-4o-2024-08-06, thinking· U-MATH and mu-MATH95.3%
7QwQ 32B Previewalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH95.3%
8Qwen2.5 Math 72B Instructalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH94.7%
9QVQ 72B Previewalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH94%
10Qwen2.5 32B Instructalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH92%
11Gemini 1.5 Proalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH91.3%
12Gemini 1.5 Flashalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH90.7%
13Qwen2.5 72B Instructalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH90.7%
14GPT 4oalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH90%
15Gemini 2.0 Flash Experimentalalgebra, all, gpt-4o-2024-08-06, thinking· U-MATH and mu-MATH89.4%
16o1algebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH89.4%
17Phi 4algebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH89.3%
18O1 Minialgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH87.8%
19GPT-4o minialgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH87.3%
20Gemini 1.5 Proalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH86.1%
21Qwen2.5 7B Instructalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH86%
22Mistral Large Instruct 2411algebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH85.3%
23Qwen2.5 Math 7B Instructalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH84.7%
24o3 Minialgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH84.4%
25Nvidia Llama 3.1 Nemotron 70B Instructalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH84%
26QVQ 72B Previewalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH83.9%
27DeepSeek R1algebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH83.3%
28Gemini 1.5 Flashalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH83.3%
29Llama 3.3 70B Instructalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH83.3%
30Llama 3.2 90B Vision Instructalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH82%
31DeepSeek V3algebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH81.7%
32Phi 4algebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH81.7%
33GPT 4oalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH80.6%
34Qwen2-VL (72B) Instructalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH80%
35Qwen2.5 Math 72B Instructalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH80%
36QwQ 32B Previewalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH80%
37Qwen2.5 32B Instructalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH78.9%
38Llama 3.1 70B Instructalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH78.7%
39Qwen2.5 72B Instructalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH78.3%
40Claude 3.5 Sonnetalgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH75.3%
41GPT-4o minialgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH75%
42Qwen2.5 7B Instructalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH75%
43Nvidia Llama 3.1 Nemotron 70B Instructalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH73.9%
44Mistral Large Instruct 2411algebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH73.3%
45Llama 3.2 90B Vision Instructalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH72.2%
46Qwen2.5 Math 7B Instructalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH71.7%
47Qwen2-VL (72B) Instructalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH71.1%
48Llama 3.3 70B Instructalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH70.6%
49Claude 3.5 Sonnetalgebra, all, gpt-4o-2024-08-06· U-MATH and mu-MATH67.8%
50LFM-7balgebra, text, gpt-4o-2024-08-06· U-MATH and mu-MATH66.7%

Showing 1–50 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)