Skip to content

Benchmark

Vals MysteryMechanism

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

Models measured
32
Scores recorded
32
Sources
1
IQ weight
2.29

Score distribution

31.6%
Mean
30.2%
Median
12.2%
Std dev
18.5%
10th percentile
49.6%
90th percentile
12.2%
Min
12.2%53.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.29 for chat models, measured over 32 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard