LegalCiteBench - Citation Completion: leaderboard
LegalCiteBench (2026) tests whether LLMs, without retrieval, can recover and verify the case authorities cited in 1,000 U.S. judicial opinions from the Case Law Access Project. In citation completion the model supplies the source-opinion authorities missing from a partial citation list; citation-level F1 from 0 to 100, higher is better.
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 2037. 21 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 6.35 | #261 |
| 2 | Qwen 3 14B | 6.34 | #1269 |
| 3 | DeepSeek V3.1 | 5.15 | #511 |
| 4 | DeepSeek R1 Distill Qwen 1.5B | 4.54 | #9215 |
| 5 | Qwen 3 30B A3B | 4.34 | #1156 |
| 6 | Llama 3.1 70B | 4.34 | #1499 |
| 7 | O4 Mini | 4.06 | #368 |
| 8 | SaulLM-54B | 4.06 | |
| 9 | Claude Haiku 4.5 | 3.87 | #583 |
| 10 | Gemini 2.5 Flash | 3.66 | #463 |
| 11 | Qwen 2.5 7B | 3.5 | #2929 |
| 12 | DeepSeek-R1-Distill-Qwen-7B | 3.49 | #8055 |
| 13 | Qwen 3 4B | 3.37 | #2348 |
| 14 | Phi-4 | 3.16 | #1931 |
| 15 | Mistral 7B | 2.56 | #7794 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=legalcitebench-citation-completion · How It Works · Data refreshed daily, snapshot 2026-11-21.