Skip to content

Benchmark

Legal Research Bench

Scores are percentages. Higher is better.

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

39.2%
Mean
44.2%
Median
5%
Std dev
34.1%
10th percentile
44.2%
90th percentile
34.1%
Min
34.1%44.2%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Kimi K3max effort · temp 1.0 · top_p 1.0· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.44.2%
2MiniMax M3.1 FlashVals AI October 20 model evaluation · official MiniMax API · temperature 1 / top_p 0.95 / compute effort max · displayed uncertainty ±3.3 percentage points · output cap inconsistent across the page· Reported by Vals AI· via BenchBoard docs34.1%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.