LegalCiteBench - Citation Completion: leaderboard
Metric: Cat2 citation-level F1 (0-100) of the remaining source-opinion authorities the model supplies given a partial citation set (4,899 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: Around 2039. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 6.35 |
| 2 | Qwen 3 14B | 6.34 |
| 3 | DeepSeek V3.1 | 5.15 |
| 4 | DeepSeek R1 Distill Qwen 1.5B | 4.54 |
| 5 | Qwen 3 30B A3B | 4.34 |
| 6 | Llama 3.1 70B | 4.34 |
| 7 | O4 Mini | 4.06 |
| 8 | Claude Haiku 4.5 | 3.87 |
| 9 | Gemini 2.5 Flash | 3.66 |
| 10 | Qwen 2.5 7B | 3.5 |
| 11 | DeepSeek-R1-Distill-Qwen-7B | 3.49 |
| 12 | Qwen 3 4B | 3.37 |
| 13 | Phi-4 | 3.16 |
| 14 | Mistral 7B | 2.56 |
| 15 | GPT-4o Mini | 2.27 |
Interactive version: theaggregate.ai/benchmark?slug=legalcitebench-citation-completion · How It Works · Data refreshed daily, snapshot 2026-10-07.