IslamicLegalBench - Low Complexity — leaderboard
Metric: Weighted Accuracy (%). Source: huggingface.co. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 83.53 |
| 2 | Claude Sonnet 4.5 | 79.17 |
| 3 | Gemini 2.5 Pro | 79.12 |
| 4 | Grok 4 | 76.77 |
| 5 | Llama 4 Maverick Instruct FP8 | 66.68 |
| 6 | DeepSeek R1 | 65.34 |
| 7 | Qwen 3 235B A22B 2507 Instruct | 60.13 |
| 8 | GPT-OSS-120B | 45.03 |
| 9 | Llama 3.1 8B Instruct | 41.9 |
Interactive version: theaggregate.ai/benchmark?slug=islamiclegalbench-low-complexity · How the rankings work · Data refreshed daily, snapshot 2026-07-22.