Skip to content

Benchmark

Vals ProofBench v1.1

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

Models measured
52
Scores recorded
52
Sources
1
IQ weight
1.49

Score distribution

55.4%
Mean
58%
Median
32.4%
Std dev
10%
10th percentile
99%
90th percentile
0%
Min
0%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.49 for chat models, measured over 52 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 1–50 of 52 results.