Eye-Q - Basic - Arabic: leaderboard
Metric: Exact-Match Accuracy (%; basic prompt with the answer length in characters, Arabic subset). Source: arxiv.org. Saturation forecast: Around August 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 14.89 |
| 2 | Grok 4.1 Fast (Reasoning) | 6.38 |
| 3 | GPT-5.2 (Non-reasoning) | 6.38 |
| 4 | Gemini 2.5 Flash | 2.13 |
| 5 | Llama 4 Scout | 0 |
| 6 | Qwen 3 VL 235B A22B Instruct | 0 |
Interactive version: theaggregate.ai/benchmark?slug=eye-q-basic-arabic · How It Works · Data refreshed daily, snapshot 2026-09-25.