Skip to content

Benchmark

Vals Legal Research Bench

Scores are percentages.

Models measured
93
Scores recorded
93
Sources
1
IQ weight
2.40

Score distribution

33.2%
Mean
38%
Median
14.8%
Std dev
10.6%
10th percentile
49.5%
90th percentile
0.962%
Min
0.962%55.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.40 for chat models, measured over 93 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 51–93 of 93 results.