ContrAR (Single Frame) - Smart Apartment: leaderboard

ContrAR (2026) tests whether vision-language models detect contradictory virtual content attacks in augmented reality, answering yes or no on real AR videos of which half carry an overlay that contradicts the physical scene, given the middle frame of each video. Detection accuracy in percent on the smart apartment videos; higher is better.

Metric: Detection accuracy (%) for contradictory virtual content attacks in AR videos (90 smart apartment videos; half the videos carry a contradiction, a balanced yes/no decision), one middle frame of each video given (single-frame prompting); mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-594.44#178
2Gemini 2.5 Flash88.89#463
3Gemini 2.5 Pro86.67#276
4GPT-4.184.44#505
5GPT-4o77.78#751
6Claude Sonnet 4.564.44#261
7Qwen 2.5 VL 72B Instruct62.22#841
8Grok 461.11#319
9Qwen 2.5 VL 7B Instruct57.78#1902
10Grok 2 Vision57.78#1437
11Claude Haiku 4.548.89#583

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=contrar-single-frame-smart-apartment · How It Works · Data refreshed daily, snapshot 2026-11-21.