Skip to content

Benchmark

Vals MATH 500

Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.

Models measured
49
Scores recorded
54
Sources
1
IQ weight
2.52

Score distribution

83.5%
Mean
89%
Median
13.8%
Std dev
70.2%
10th percentile
94.8%
90th percentile
25.4%
Min
25.4%96.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.52 for chat models, measured over 49 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 51–54 of 54 results.