IslamicMMLU - Surah Identification: leaderboard
Metric: Accuracy (%) on IslamicMMLU's 833 Quran track questions on naming the surah a verse comes from, against lexically similar distractors; four-option multiple choice in Arabic, zero-shot, temperature 0, answer letter only (10 new tokens), via each model's API; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 26 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 99.4 | #93 |
| 2 | Gemini 3 Pro | 97.5 | #77 |
| 3 | GPT-5 | 96.6 | #91 |
| 4 | Claude Opus 4.5 | 96 | #79 |
| 5 | Gemini 2.5 Pro | 94.2 | #145 |
| 6 | GPT-5.2 | 92 | #105 |
| 7 | GPT-5.1 | 91.8 | #131 |
| 8 | Claude Sonnet 4.5 | 90.4 | #138 |
| 9 | Gemini 2.5 Flash | 86.2 | #237 |
| 10 | Claude 3.7 Sonnet | 83.9 | #241 |
| 11 | DeepSeek V3.2 | 78.5 | #198 |
| 12 | DeepSeek V3.1 | 76.8 | #260 |
| 13 | Grok 4.1 Fast | 76.5 | #208 |
| 14 | GPT-4o | 71.1 | #333 |
| 15 | GPT-4.1 | 69.2 | #240 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=islamicmmlu-surah-identification · How It Works · Data refreshed daily, snapshot 2026-10-11.