# Harvey's Legal Agent Benchmark — AI model rankings

Harvey's test of whether an AI agent can complete real legal work — drafting and reviewing documents, working with spreadsheets and presentations, and navigating files the way a lawyer's assistant would. Higher is better.

10 tracked models have a published Harvey's Legal Agent Benchmark 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 | Muse Spark 1.1 | Meta | 20% | Lab | Jul 9 2026 |
| 2 | Grok 4.7 | SpaceXAI | 19.6% | Lab | Sep 21 2026 |
| 2 | Gemini 4 Argon | Google | 19.6% | Lab | Sep 30 2026 |
| 4 | Grok 4.6 | SpaceXAI | 15.8% | Lab | Aug 12 2026 |
| 5 | Grok 4.5 | SpaceXAI | 12.92% | Lab | Jul 8 2026 |
| 6 | Claude Fable 5 | Anthropic | 11.25% | Lab | Jun 9 2026 |
| 7 | Gemini 3.8 Flash | Google | 10% | Lab | Sep 2 2026 |
| 8 | Claude Opus 4.8 | Anthropic | 9.58% | Lab | May 28 2026 |
| 9 | Gemini 3.7 Flash | Google | 8.8% | Lab | Aug 13 2026 |
| 10 | GPT-5.5 | OpenAI | 3.75% | Lab | Apr 23 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/harvey-legal-agent
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.