IslamicLegalBench - High Complexity — leaderboard
Metric: Weighted Accuracy (%). Source: huggingface.co. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 75.5 |
| 2 | Gemini 2.5 Pro | 73.12 |
| 3 | GPT-5 | 72.99 |
| 4 | Grok 4 | 72.88 |
| 5 | Qwen 3 235B A22B 2507 Instruct | 67.65 |
| 6 | DeepSeek R1 | 66.51 |
| 7 | Llama 4 Maverick Instruct FP8 | 55.14 |
| 8 | Llama 3.1 8B Instruct | 52.99 |
| 9 | GPT-OSS-120B | 50.7 |
Interactive version: theaggregate.ai/benchmark?slug=islamiclegalbench-high-complexity · How the rankings work · Data refreshed daily, snapshot 2026-07-22.