Legal AI Solution Design MapInterpreting benchmarks for legal work and system design.
Menu

30 benchmarks · evidence refreshed 30 October 2026

Aced the exam, but
can legal AI do the job?

Benchmaxxed describes AI that is optimised to perform well on benchmarks rather than necessarily becoming better at real-world work. This site maps 30 legal AI benchmark results to actual legal skills and tasks to test what those scores really tell us about the current state of legal AI, and offer design suggestions for known trouble spots.

Individual criteria versus whole-task completion

96.3%of individual criteria passed
HLAB-Vals-1.1 · same evaluation
27.1%of whole tasks resolved

Gemini 4 Argon on Vals’ HLAB-Vals-1.1, checked 30 October 2026. A task passes only when every criterion passes. Strong individual steps still do not ensure complete work. Read the updated scoring and version caveats.

Benchmark coverage by task

ScoredMapped, no score—Nothing recorded