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.
LLM Stats
Legal Agent Benchmark
The Legal Agent Benchmark (LAB) is Harvey's open-source benchmark for evaluating AI agents on complex, long-horizon legal work. Tasks are scored under an all-pass standard against expert-curated rubrics, where a task passes only if every required rubric criterion (facts, conclusions, citations, structure, and analytical moves) passes.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- text
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 13
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Claude Fable 5 | 0.133 | Not recorded | Not recorded | 2026-06-09 · model_announcement | LLM Stats |
| Claude Opus 5 | 0.117 | Not recorded | Not recorded | 2026-07-24 · model_announcement | LLM Stats |
| Claude Opus 4.7 | 0.071 | Not recorded | Not recorded | 2026-04-16 · model_announcement | LLM Stats |
| Claude Sonnet 5 | 0.058 | Not recorded | Not recorded | 2026-06-30 · model_announcement | LLM Stats |
| Claude Sonnet 4.6 | 0.054 | Not recorded | Not recorded | 2026-02-17 · model_announcement | LLM Stats |
| Claude Opus 4.6 | 0.042 | Not recorded | Not recorded | 2026-02-05 · model_announcement | LLM Stats |
| GPT-5.5 | 0.021 | Not recorded | Not recorded | 2026-04-23 · model_announcement | LLM Stats |
| Gemini 3.5 Flash | 0.008 | Not recorded | Not recorded | 2026-05-19 · model_announcement | LLM Stats |
| GPT-5.4 | 0.004 | Not recorded | Not recorded | 2026-03-05 · model_announcement | LLM Stats |
| GPT-5.4 mini | 0.0 | Not recorded | Not recorded | 2026-03-17 · model_announcement | LLM Stats |
| Gemini 3.1 Flash-Lite | 0.0 | Not recorded | Not recorded | 2026-03-03 · model_announcement | LLM Stats |
| Gemini 3.1 Pro | 0.0 | Not recorded | Not recorded | 2026-02-19 · model_announcement | LLM Stats |
| Gemini 3 Flash | 0.0 | Not recorded | Not recorded | 2025-12-17 · model_announcement | LLM Stats |