VisualTextTrap (VideoMME) - Hallucination Resistance: leaderboard
Text overlay-induced hallucination in video question answering on VisualTextTrap (2026), built on VideoMME videos with on-screen text that agrees with, contradicts or is absent from the visual evidence. Accuracy on the text-contradictory samples, in percent; higher is better.
Metric: Hallucination resistance rate (%): accuracy on the text-contradictory samples of the VisualTextTrap videos built on VideoMME (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) | 60.1 | #99 |
| 2 | Qwen 3 VL 235B A22B | 42.6 | #485 |
| 3 | InternVL3.5-241B-A28B | 38.4 | #733 |
| 4 | Qwen 3 VL 30B A3B | 34.7 | #784 |
| 5 | Qwen 3 VL 8B Instruct | 28.4 | #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-videomme-hallucination-resistance · How It Works · Data refreshed daily, snapshot 2026-11-21.