Arabic Broad Leaderboard - MMLU: leaderboard
MMLU-style Arabic multiple-choice knowledge questions: the 121-question MMLU category of SILMA's Arabic Broad Benchmark, whose answers are scored 0-10 by rules or an LLM judge. Category average score (0-10), higher is better; each model's latest result file is used.
Metric: Average Score (0-10). Source: huggingface.co. Saturation forecast: Estimated already saturated. 121 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Flash Lite | 10 | #200 |
| 2 | GPT-5.2 | 9.92 | #115 |
| 3 | GPT-6.1 Pro Sol | 9.92 | #11 |
| 4 | Qwen 3.5 397B A17B | 9.84 | #154 |
| 5 | Claude 3.7 Sonnet (20250219) | 9.84 | #209 |
| 6 | Gemini 3.7 Flash | 9.84 | #24 |
| 7 | Muse Spark 1.1 | 9.84 | #55 |
| 8 | c4ai-command-a-03-2025 | 9.84 | #468 |
| 9 | Qwen 3.5 27B | 9.75 | #192 |
| 10 | Gemini 3.5 Flash | 9.75 | #66 |
| 11 | Gemini 3.8 Flash | 9.75 | #30 |
| 12 | Gemini 4 Argon | 9.75 | #9 |
| 13 | Grok 4.7 | 9.75 | #26 |
| 14 | Muse Glimmer 30B | 9.75 | #191 |
| 15 | Gemma 4 31B (IT) | 9.67 | #178 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=arabic-broad-leaderboard-mmlu · How It Works · Data refreshed daily, snapshot 2026-11-05.