LegalCiteBench - Citation Error Detection: 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 error detection the model finds and corrects wrong citations in legal analysis paragraphs; judge score from 0 to 100, higher is better.
Metric: Cat3 judge score (0-100) for detecting citation errors in legal analysis paragraphs and supplying the correct citation (5,474 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. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | SaulLM-54B | 75.59 | |
| 2 | DeepSeek-R1-Distill-Qwen-7B | 58.71 | #8055 |
| 3 | DeepSeek R1 Distill Qwen 1.5B | 58.11 | #9215 |
| 4 | GPT-5 Mini | 54.95 | #364 |
| 5 | Qwen 3 14B | 52.18 | #1269 |
| 6 | Qwen 3 4B | 47.12 | #2348 |
| 7 | Gemini 2.5 Flash | 46.93 | #463 |
| 8 | O4 Mini | 46.71 | #368 |
| 9 | Llama 3.1 8B | 45.32 | #5196 |
| 10 | Claude Sonnet 4.5 | 44.87 | #261 |
| 11 | Qwen 3 30B A3B | 43.55 | #1156 |
| 12 | Mistral 7B | 43.4 | #7794 |
| 13 | Phi-4 | 43.35 | #1931 |
| 14 | Claude Haiku 4.5 | 43.01 | #583 |
| 15 | GPT-4o Mini | 42.84 | #1667 |
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-error-detection · How It Works · Data refreshed daily, snapshot 2026-11-21.