HELM Lite - LegalBench - International Citizenship Questions: leaderboard

Metric: Exact Match (%). Source: crfm.stanford.edu. 91 models tracked.

Top models

#ModelScore
1Llama 3 70B70.5
2Gemini 1.5 Pro (002)68.5
3Gemini 1.5 Pro (001)67.5
4Nova Lite65.8
5GPT-4 Turbo65.6
6Nova Pro65.5
7Qwen 2 72B Instruct65.3
8Qwen 1.5 7B63.3
9Qwen 2.5 72B Instruct63.1
10GPT-4 (0613)63
11Nova Micro62.9
12Llama 2 70B62
13Llama 2 13B61.8
14Qwen 1.5 72B61.2
15Qwen 1.5 14B60.9

Interactive version: theaggregate.ai/benchmark?slug=helm-lite-legalbench-international-citizenship-questions · How It Works · Data refreshed daily, snapshot 2026-09-19.