DLawBench: leaderboard
Metric: Resolution score (0-100), a rate scaled by 100: mean of fact resolution (annotated facts carried into the legal memo and correctly preserved or reframed against the court record) and issue resolution (expert-specified legal analysis points addressed), averaged over the two jurisdictions, on 461 real Chinese-law and U.S.-law cases replayed as multi-turn consultations with a Claude Sonnet 4.6 client simulator in four narrative styles; judged by a GPT-5.1, Claude Opus 4.6 and Gemini 3.1 Pro panel (median; same-vendor judges recuse), empty memos count as zero; provider decoding defaults; higher is better. Source: arxiv.org. Saturation forecast: Around July 2027. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 56.2 |
| 2 | GPT-5.4 | 54.6 |
| 3 | GPT-5.2 | 49.9 |
| 4 | Gemini 3.1 Pro (Preview) | 47.2 |
| 5 | Claude Opus 4.7 | 44 |
| 6 | Qwen 3.6 Max Preview | 43.5 |
| 7 | Claude Opus 4.6 | 43.3 |
| 8 | Kimi K2.6 | 42.4 |
| 9 | GLM-5.1 | 41.8 |
| 10 | DeepSeek V4 Pro | 41.5 |
| 11 | Kimi K2.5 | 39.7 |
| 12 | Claude Sonnet 4.6 | 37.6 |
| 13 | Qwen 3.6 Plus | 37.2 |
| 14 | GLM-5 | 36.5 |
| 15 | Grok 4.1 Fast | 34.9 |
Interactive version: theaggregate.ai/benchmark?slug=dlawbench · How It Works · Data refreshed daily, snapshot 2026-09-29.