Eye-Q - Partial Character Reveal - Arabic: leaderboard
Eye-Q (Najar et al., 2026), Arabic visual word puzzles (50 synthetic scenes written by the authors): each image encodes a hidden word or phrase through visual cues, and the model must output the exact target. A random 25% of the answer's characters are shown and the rest masked. Exact-match accuracy in percent; higher is better.
Metric: Exact-Match Accuracy (%; 25% of the answer's characters revealed, Arabic subset). Source: arxiv.org. Saturation forecast: Around March 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 17.02 | #262 |
| 2 | Grok 4.1 Fast (Reasoning) | 17.02 | #426 (Grok 4.1 Fast) |
| 3 | Gemini 2.5 Flash | 10.64 | #452 |
| 4 | GPT-5.2 (Non-reasoning) | 4.26 | #172 (GPT-5.2) |
| 5 | Qwen 3 VL 235B A22B Instruct | 2.13 | #521 |
| 6 | Llama 4 Scout | 0 | #1787 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=eye-q-partial-character-reveal-arabic · How It Works · Data refreshed daily, snapshot 2026-11-12.