LegalCiteBench - Case Verification: leaderboard
Metric: Cat4-2 judge score (0-100) for verifying whether a cited case supports a stated legal principle and supplying the correct case when it does not (6,377 instances), closed-book (no retrieval) on instances derived from 1,000 U.S. judicial opinions of the Case Law Access Project, greedy decoding at temperature 0 with at most 400 generated tokens, GPT-4o-mini judge; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral 7B | 96.07 |
| 2 | DeepSeek-R1-Distill-Qwen-7B | 91.44 |
| 3 | DeepSeek R1 Distill Qwen 1.5B | 90.81 |
| 4 | Gemini 2.5 Flash | 89.88 |
| 5 | Qwen 3 14B | 89.58 |
| 6 | Qwen 2.5 7B | 89.32 |
| 7 | Llama 3.1 70B | 89 |
| 8 | GPT-5 Mini | 88.28 |
| 9 | Gemma 3 12B | 85.91 |
| 10 | O4 Mini | 80.12 |
| 11 | DeepSeek V3.1 | 78.16 |
| 12 | Llama 3.2 3B | 78.1 |
| 13 | Qwen 3 30B A3B | 78.04 |
| 14 | Llama 3.1 8B | 76.31 |
| 15 | Phi-4 | 74.82 |
Interactive version: theaggregate.ai/benchmark?slug=legalcitebench-case-verification · How It Works · Data refreshed daily, snapshot 2026-10-07.