IslamicLegalBench - Moderate Complexity — leaderboard
Metric: Weighted Accuracy (%). Source: huggingface.co. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 68.98 |
| 2 | Claude Sonnet 4.5 | 65.99 |
| 3 | Gemini 2.5 Pro | 63.05 |
| 4 | Grok 4 | 61.76 |
| 5 | DeepSeek R1 | 56.71 |
| 6 | Llama 4 Maverick Instruct FP8 | 52.17 |
| 7 | Qwen 3 235B A22B 2507 Instruct | 50.88 |
| 8 | GPT-OSS-120B | 44 |
| 9 | Llama 3.1 8B Instruct | 34.65 |
Interactive version: theaggregate.ai/benchmark?slug=islamiclegalbench-moderate-complexity · How the rankings work · Data refreshed daily, snapshot 2026-07-22.