Arabic Broad Leaderboard - General Knowledge: leaderboard
Arabic general-knowledge questions: the 63-question General Knowledge 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 Pro (Preview) | 9.65 | #71 |
| 2 | GPT-4o | 9.44 | #357 |
| 3 | O3 | 9.44 | #132 |
| 4 | Claude Opus 4.7 | 9.41 | #51 |
| 5 | GPT-5.2 | 9.32 | #115 |
| 6 | Gemini 2.0 Flash | 9.32 | #351 |
| 7 | Gemini 3.5 Flash | 9.27 | #66 |
| 8 | Claude 3.7 Sonnet (20250219) | 9.24 | #209 |
| 9 | Gemini 3.1 Flash Lite | 9.22 | #200 |
| 10 | Gemini 2.5 Flash (Preview 04-17) | 9.21 | #246 |
| 11 | Gemini 2.5 Pro (Preview 05-06) | 9.21 | #156 |
| 12 | GPT-4.1 Mini | 9.19 | #363 |
| 13 | MiniMax-M3 | 9.18 | #151 |
| 14 | Gemini 4 Argon | 9.18 | #9 |
| 15 | Gemma 4 31B (IT) | 9.16 | #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-general-knowledge · How It Works · Data refreshed daily, snapshot 2026-11-05.