LegalCiteBench - Case Matching: 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 case matching the model identifies the source case of an anonymized legal scenario; judge score from 0 to 100, higher is better.

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. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5 Mini74#364
2DeepSeek-R1-Distill-Qwen-7B55.53#8055
3DeepSeek R1 Distill Qwen 1.5B53.42#9215
4Qwen 3 14B43.26#1269
5Qwen 2.5 7B43.24#2929
6O4 Mini42.39#368
7DeepSeek V3.142.29#511
8Claude Sonnet 4.541.64#261
9Gemini 2.5 Flash41.12#463
10Claude Haiku 4.540.56#583
11Phi-440.32#1931
12Llama 3.1 8B40.24#5196
13Qwen 3 4B40.05#2348
14GPT-4o Mini39.54#1667
15Qwen 3 30B A3B39.32#1156

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=legalcitebench-case-matching · How It Works · Data refreshed daily, snapshot 2026-11-21.