Skip to content

Benchmark

Artificial Analysis Legal Index

Scores are index points out of 100.

Scores from OpenRouter data docs.
Models measured
67
Scores recorded
67
Sources
1
IQ weight
1.64

Score distribution

35.1
Mean
35.1
Median
15
Std dev
14.6
10th percentile
55
90th percentile
6.9
Min
6.963.8
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.64 for chat models, measured over 67 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 51–67 of 67 results.