SAHM - Fatwa MCQ: leaderboard
Metric: Accuracy (%) on the 2,000 Islamic financial fatwa multiple-choice questions of SAHM, an Arabic financial and Sharia-compliance benchmark, exact match after normalizing the chosen option, greedy decoding, mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.5 | 91.75 |
| 2 | GPT-5 | 90.75 |
| 3 | Gemini 3 Flash (Preview) | 89.9 |
| 4 | Claude Sonnet 4.5 | 88.15 |
| 5 | GPT-4o | 87.7 |
| 6 | Llama 3.1 70B Instruct | 84.9 |
| 7 | Claude Haiku 4.5 | 84.9 |
| 8 | Qwen 2.5 72B Instruct | 84.65 |
| 9 | GPT-4o Mini | 81.75 |
| 10 | Gemma 3 27B (IT) | 80.65 |
| 11 | Qwen 2.5 14B Instruct | 76.05 |
| 12 | Fanar-1-9B-Instruct | 74.45 |
| 13 | ALLaM-7B-Instruct-preview | 74.4 |
| 14 | Qwen 2.5 7B Instruct | 70 |
| 15 | Gemma 2 9B (IT) | 66.6 |
Interactive version: theaggregate.ai/benchmark?slug=sahm-fatwa-mcq · How It Works · Data refreshed daily, snapshot 2026-10-07.