Skip to content

Benchmark

BigLaw Bench

Scores are percentages. Higher is better.

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

Score distribution

91%
Mean
91%
Median
0.05%
Std dev
90.9%
10th percentile
91%
90th percentile
90.9%
Min
90.9%91%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1GPT 5.4Harvey evaluation· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91%
2Claude Opus 4.7Harvey internal evaluation · high effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.9%

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.