IslamicMMLU - Verse Count: leaderboard

Metric: Accuracy (%) on IslamicMMLU's 114 Quran track questions on giving the number of verses in a surah; 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

#ModelScoreOverall rank
1Gemini 2.5 Pro100#145
2GPT-5100#91
3Gemini 3 Flash100#93
4Gemini 3 Pro100#77
5GPT-5.1100#131
6Grok 4.1 Fast100#208
7DeepSeek V3.299.1#198
8Claude Opus 4.599.1#79
9Claude Sonnet 4.598.2#138
10DeepSeek V3.195.6#260
11Llama 4 Maverick94.7#451
12Claude 3.7 Sonnet94.7#241
13Gemini 2.5 Flash93.9#237
14Claude Haiku 4.584.2#271
15GPT-5.281.6#105

No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.

Interactive version: theaggregate.ai/benchmark?slug=islamicmmlu-verse-count · How It Works · Data refreshed daily, snapshot 2026-10-11.