LegalCiteBench - Case Matching: leaderboard
Metric: Cat4-1 judge score (0-100) for matching an anonymized legal scenario to its source case name and citation (1,997 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 | GPT-5 Mini | 74 |
| 2 | DeepSeek-R1-Distill-Qwen-7B | 55.53 |
| 3 | DeepSeek R1 Distill Qwen 1.5B | 53.42 |
| 4 | Qwen 3 14B | 43.26 |
| 5 | Qwen 2.5 7B | 43.24 |
| 6 | O4 Mini | 42.39 |
| 7 | DeepSeek V3.1 | 42.29 |
| 8 | Claude Sonnet 4.5 | 41.64 |
| 9 | Gemini 2.5 Flash | 41.12 |
| 10 | Claude Haiku 4.5 | 40.56 |
| 11 | Phi-4 | 40.32 |
| 12 | Llama 3.1 8B | 40.24 |
| 13 | Qwen 3 4B | 40.05 |
| 14 | GPT-4o Mini | 39.54 |
| 15 | Qwen 3 30B A3B | 39.32 |
Interactive version: theaggregate.ai/benchmark?slug=legalcitebench-case-matching · How It Works · Data refreshed daily, snapshot 2026-10-07.