Skip to content

Benchmark

U-MATH sequences_series 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
1.63

Score distribution

44.8%
Mean
48.7%
Median
27.3%
Std dev
0%
10th percentile
84.4%
90th percentile
0%
Min
0%94%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.63 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 Minisequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH94%
2o3 Minisequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH93.5%
3DeepSeek R1sequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH93.3%
4o1sequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH93.3%
5DeepSeek R1sequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH92.9%
6o1sequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH92.9%
7Gemini 2.0 Flash Experimentalsequences_series, text, gpt-4o-2024-08-06, thinking· U-MATH and mu-MATH90%
8Gemini 2.0 Flash Experimentalsequences_series, all, gpt-4o-2024-08-06, thinking· U-MATH and mu-MATH88.3%
9QwQ 32B Previewsequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH85.3%
10QwQ 32B Previewsequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH84.4%
11O1 Minisequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH77.3%
12O1 Minisequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH76.6%
13DeepSeek R1sequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH75%
14o1sequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH75%
15o3 Minisequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH75%
16Qwen2.5 Math 72B Instructsequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH75%
17DeepSeek V3sequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH72.7%
18DeepSeek V3sequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH72.1%
19Qwen2.5 Math 72B Instructsequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH68.8%
20Qwen2.5 Math 72B Instructsequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH68.7%
21QVQ 72B Previewsequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH68%
22QVQ 72B Previewsequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH66.2%
23Gemini 1.5 Prosequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH63.3%
24Gemini 1.5 Prosequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH63%
25Gemini 1.5 Flashsequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH60.7%
26Gemini 1.5 Flashsequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH60.4%
27Qwen2.5 32B Instructsequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH58%
28Qwen2.5 32B Instructsequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH56.5%
29Mistral Large Instruct 2411sequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH56%
30Mistral Large Instruct 2411sequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH55.2%
31Qwen2.5 72B Instructsequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH54.7%
32Qwen2.5 72B Instructsequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH54.5%
33Qwen2.5 Math 7B Instructsequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH52%
34Qwen2.5 Math 7B Instructsequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH51.9%
35DeepSeek V3sequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH50%
36Gemini 1.5 Flashsequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH50%
37Gemini 1.5 Prosequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH50%
38GPT-4o minisequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH50%
39Llama 3.1 70B Instructsequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH50%
40O1 Minisequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH50%
41Phi 4sequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH50%
42Qwen2.5 72B Instructsequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH50%
43Qwen2.5 Math 7B Instructsequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH50%
44QwQ 32B Previewsequences_series, visual, gpt-4o-2024-08-06· U-MATH and mu-MATH50%
45Phi 4sequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH48.7%
46GPT 4osequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH46.7%
47Llama 3.3 70B Instructsequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH46.7%
48Llama 3.3 70B Instructsequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH46.1%
49GPT 4osequences_series, all, gpt-4o-2024-08-06· U-MATH and mu-MATH45.5%
50Nvidia Llama 3.1 Nemotron 70B Instructsequences_series, text, gpt-4o-2024-08-06· U-MATH and mu-MATH43.3%

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)