LexGenius: leaderboard
Expert-level benchmark for legal general intelligence, covering Chinese legal understanding and reasoning across multiple task dimensions.
Metric: CoT average (self-reported). Source: benchmarklist.com. Status: saturated. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek R1 | 64.59 |
| 2 | DeepSeek V3 | 64.39 |
| 3 | Qwen 2.5 7B | 59.38 |
| 4 | Qwen 3 8B | 55.3 |
| 5 | GPT-4.1 Nano | 53.43 |
| 6 | Qwen 3 4B | 53.19 |
| 7 | GPT-4o Mini | 52.61 |
Interactive version: theaggregate.ai/benchmark?slug=lexgenius · How It Works · Data refreshed daily, snapshot 2026-09-05.