Cedar - Text-Only - Arabic: leaderboard
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around May 2028. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash (Thinking) | 51.48 |
| 2 | Claude Sonnet 4.5 | 49.69 |
| 3 | Qwen 3 VL 235B A22B (Thinking) | 47.95 |
| 4 | GPT-4o (2024-11-20) | 46.56 |
| 5 | Kimi K2 | 44.15 |
| 6 | Qwen 3 VL 8B (Thinking) | 39.36 |
| 7 | Gemma 3 27B (IT) | 39.13 |
| 8 | aya-vision-8B | 36 |
| 9 | Pixtral-12B-2409 | 32.65 |
| 10 | Mistral Small 3.2 | 20.12 |
Interactive version: theaggregate.ai/benchmark?slug=cedar-text-only-arabic · How It Works · Data refreshed daily, snapshot 2026-09-25.