LegalCiteBench: leaderboard
Metric: Overall (Norm.) (self-reported). Source: benchmarklist.com. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 77.8 |
| 2 | Qwen 3 14B | 71.6 |
| 3 | DeepSeek V3.1 | 70.5 |
| 4 | O4 Mini | 70.1 |
| 5 | Gemini 2.5 Flash | 69.1 |
| 6 | Llama 3.1 70B | 64.3 |
| 7 | GPT-5 Mini | 63.5 |
| 8 | Qwen 3 30B A3B | 62.8 |
| 9 | Claude Haiku 4.5 | 62.4 |
| 10 | Qwen 3 4B | 59 |
| 11 | Phi-4 | 58.5 |
| 12 | Mistral 7B | 58.5 |
| 13 | Qwen 2.5 7B | 54.7 |
| 14 | Gemma 3 12B | 50.7 |
| 15 | GPT-4o Mini | 50.2 |
Interactive version: theaggregate.ai/benchmark?slug=legalcitebench · How It Works · Data refreshed daily, snapshot 2026-09-05.