Eye-Q - Partial Character Reveal - English: leaderboard
Metric: Exact-Match Accuracy (%; 25% of the answer's characters revealed, English subset). Source: arxiv.org. Saturation forecast: Around December 2026. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Grok 4.1 Fast (Reasoning) | 60.27 |
| 2 | Gemini 2.5 Pro | 51.52 |
| 3 | GPT-5.2 (Non-reasoning) | 31.99 |
| 4 | Gemini 2.5 Flash | 29.29 |
| 5 | Qwen 3 VL 235B A22B Instruct | 15.49 |
| 6 | Llama 4 Scout | 9.76 |
Interactive version: theaggregate.ai/benchmark?slug=eye-q-partial-character-reveal-english · How It Works · Data refreshed daily, snapshot 2026-09-25.