# Harvey's Legal Agent Benchmark (Held-out) — AI model rankings

Harvey's test of whether an AI agent can complete real legal work, scored on a held-out set of tasks the model makers never see — making the numbers harder to game. Higher is better.

1 tracked model have a published Harvey's Legal Agent Benchmark (Held-out) score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | Claude Opus 5 | Anthropic | 11.7% | Lab | Jul 24 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/harvey-legal-agent-heldout
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.