Harvey HLAB - Criteria Pass Rate - Employment Labor
Professional Work · 2026-05-06
The Employment Labor practice-area split of Harvey's Legal Agent Benchmark held-out evaluation criteria pass rate. This reports pooled rubric criteria passed within that split and is distinct from the all-pass task-score split.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5 | 87.6 |
| Kimi K3 | 87.6 |
| Muse Spark 1.1 | 87.3 |
| Grok 4.5 | 85.4 |
| Opus 4.8 | 82.8 |
| Claude Opus 5 | 82.4 |
| Sonnet 5 | 82.0 |
| GLM-5.2 | 81.3 |
| Sonnet 4.6 | 78.7 |
| MiniMax M3 | 77.9 |
| Gemini 3.6 Flash | 76.8 |
| GPT-5.6 Luna | 76.8 |
| Qwen3.7-Max | 76.8 |
| GPT-5.5 | 76.4 |
| DeepSeek-V4-Pro | 74.9 |
| GPT-5.6 Terra | 73.4 |
| Kimi K2.6 | 73.0 |
| GLM-5.1 | 71.9 |
| Gemini 3.5 Flash | 70.4 |
| GPT-5.6 Sol | 67.0 |
| Inkling | 67.0 |
| Gemini 3.5 Flash-Lite | 65.5 |
| GPT-5.4 | 64.8 |
| Laguna XS.2 | 61.5 |
| Qwen3.7-Plus | 56.2 |
| Grok 4.3 | 55.4 |
| Laguna M.1 | 49.4 |