Benchmarks
Models
Comparison
Vals Smith
App Reports
Government
News
Blog
Hackathon
About
Benchmarks
Models
Comparison
Vals Smith
App Reports
Government
News
Blog
Hackathon
About
Compare Models
Select models (max 7)
Grok 4.5
MiniMax-M3
Grok 4.5
MiniMax-M3
Grok 4.5
Grok 4.5
MiniMax-M3
MiniMax-M3
Legal Research Bench
Agentic US legal research
37.98%
±3.37
29.81%