AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
Model reports
Legal Agent Benchmark
Open-source agent benchmark from Harvey (github.com/harveyai/harvey- labs): 1,200+ tasks across 24 practice areas, all-pass LLM-judge grading. Absolute scores are very low across all models (0-13%), so ordering at the top is decided by a handful of tasks and small gaps are noise.
Evaluation context and evidence
- Source
- Model reports
- Publisher
- Not recorded
- Benchmark release
- 2026-05-06
- Collected
- Not recorded
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 0
This source record has no numeric results in our collection. That does not mean a score of zero or that no public results exist. Consult the original resources above.