VisualTextTrap (TemporalBench): leaderboard
Text overlay-induced hallucination in video question answering on VisualTextTrap (2026), built on TemporalBench videos with on-screen text that agrees with, contradicts or is absent from the visual evidence. Overall multiple-choice accuracy in percent; higher is better.
Metric: Overall VQA accuracy (%) on the VisualTextTrap videos built on TemporalBench (text overlays rendered on every frame under text-free, text-congruent and text-contradictory conditions, the contradictory overlays written by Claude-Sonnet-4.6), multiple-choice video QA under the default configuration of each model; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 62.5 | #99 |
| 2 | Qwen 3 VL 235B A22B | 41.6 | #485 |
| 3 | InternVL3.5-241B-A28B | 40.5 | #733 |
| 4 | Qwen 3 VL 30B A3B | 38.3 | #784 |
| 5 | Qwen 3 VL 8B Instruct | 24.2 | #1029 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=visualtexttrap-temporalbench · How It Works · Data refreshed daily, snapshot 2026-11-21.