Eye-Q - Basic - English: leaderboard
Metric: Exact-Match Accuracy (%; basic prompt with the answer length in characters, English subset). Source: arxiv.org. Saturation forecast: Around December 2026. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 42.76 |
| 2 | Grok 4.1 Fast (Reasoning) | 37.04 |
| 3 | Gemini 2.5 Flash | 20.88 |
| 4 | GPT-5.2 (Non-reasoning) | 18.18 |
| 5 | Qwen 3 VL 235B A22B Instruct | 10.44 |
| 6 | Llama 4 Scout | 6.06 |
Interactive version: theaggregate.ai/benchmark?slug=eye-q-basic-english · How It Works · Data refreshed daily, snapshot 2026-09-25.