MemEye (Full Context) - Multiple Choice: leaderboard
Metric: Exact-match accuracy (%; 371 four-option questions, averaged over four answer rotations and then macro-averaged over the 12 visual-granularity x memory-reasoning cells; full native multimodal history in context, 128k-token budget with oldest-first truncation, no memory system). Source: arxiv.org. Saturation forecast: Around December 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 Mini | 60.38 |
| 2 | Gemini 2.5 Flash Lite | 57.82 |
| 3 | GPT-4.1 Nano | 41.13 |
| 4 | Qwen 3 VL 8B Instruct | 29.74 |
Interactive version: theaggregate.ai/benchmark?slug=memeye-full-context-multiple-choice · How It Works · Data refreshed daily, snapshot 2026-09-26.