Harvey HLAB - Criteria Pass Rate - Bankruptcy Restructuring
Professional Work · 2026-05-06
The Bankruptcy Restructuring 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 |
|---|---|
| Muse Spark 1.1 | 92.0 |
| Kimi K3 | 91.0 |
| Grok 4.5 | 88.2 |
| Sonnet 4.6 | 85.8 |
| Claude Fable 5 | 84.4 |
| Claude Opus 5 | 84.1 |
| Sonnet 5 | 83.7 |
| Opus 4.8 | 83.0 |
| GPT-5.6 Luna | 81.3 |
| Gemini 3.6 Flash | 80.3 |
| MiniMax M3 | 80.3 |
| Qwen3.7-Max | 78.2 |
| DeepSeek-V4-Pro | 76.1 |
| GPT-5.5 | 76.1 |
| Gemini 3.5 Flash | 75.8 |
| GLM-5.1 | 75.4 |
| GPT-5.6 Terra | 75.4 |
| GLM-5.2 | 74.4 |
| GPT-5.6 Sol | 72.7 |
| GPT-5.4 | 68.5 |
| Gemini 3.5 Flash-Lite | 61.6 |
| Qwen3.7-Plus | 55.0 |
| Kimi K2.6 | 54.3 |
| Grok 4.3 | 52.9 |
| Inkling | 51.6 |
| Laguna XS.2 | 30.1 |
| Laguna M.1 | 11.0 |