IslamicLegalBench - Low Complexity — leaderboard

Metric: Weighted Accuracy (%). Source: huggingface.co. 12 models tracked.

Top models

#ModelScore
1GPT-583.53
2Claude Sonnet 4.579.17
3Gemini 2.5 Pro79.12
4Grok 476.77
5Llama 4 Maverick Instruct FP866.68
6DeepSeek R165.34
7Qwen 3 235B A22B 2507 Instruct60.13
8GPT-OSS-120B45.03
9Llama 3.1 8B Instruct41.9

Interactive version: theaggregate.ai/benchmark?slug=islamiclegalbench-low-complexity · How the rankings work · Data refreshed daily, snapshot 2026-07-22.