Skip to content

Benchmark

Vals MedQA

Science benchmarks measure how well models answer science questions. Scores are percentages.

Models measured
83
Scores recorded
88
Sources
1
IQ weight
2.63

Score distribution

84.3%
Mean
90.2%
Median
15.2%
Std dev
62.6%
10th percentile
95.9%
90th percentile
2.7%
Min
2.7%96.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.63 for chat models, measured over 83 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 51–88 of 88 results.