HELM Arabic - Arabic Mmlu - Islamic Studies (High School): leaderboard
Metric: Exact Match (%). Source: crfm.stanford.edu. 41 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 88.92 |
| 2 | Claude Opus 4.7 | 88.02 |
| 3 | GPT-5.4 (2026-03-05) | 85.93 |
| 4 | Gemma 4 31B (IT) | 85.03 |
| 5 | Gemini 2.5 Flash (Thinking) | 84.43 |
| 6 | GPT-4.1 (2025-04-14) | 81.14 |
| 7 | Gemini 2.5 Flash Lite (Thinking) | 79.64 |
| 8 | Claude Haiku 4.5 (20251001) | 79.04 |
| 9 | Mistral Large 3 | 78.74 |
| 10 | Qwen 3.5 397B A17B | 77.54 |
| 11 | Llama 3.3 70B Instruct | 77.25 |
| 12 | Llama 4 Maverick Instruct FP8 | 77.25 |
| 13 | DeepSeek V3.1 | 77.25 |
| 14 | Qwen 2.5 72B Instruct | 76.95 |
| 15 | Qwen 3 Next 80B A3B Instruct | 76.35 |
Interactive version: theaggregate.ai/benchmark?slug=helm-arabic-arabic-mmlu-islamic-studies-high-school · How It Works · Data refreshed daily, snapshot 2026-09-19.