Vox-Infinity - Beyond-Semantic (Text History): leaderboard
Metric: Accuracy (%; multiple-choice beyond-semantic dialogue questions, text-as-history, over all questions of the subset across its context-duration bins). Source: arxiv.org. Saturation forecast: Around April 2027. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 53.2 |
| 2 | Qwen 3.5 Plus | 52.9 |
Interactive version: theaggregate.ai/benchmark?slug=vox-infinity-beyond-semantic-text-history · How It Works · Data refreshed daily, snapshot 2026-09-26.