VURB: leaderboard

Metric: Majority-vote pairwise accuracy (%; eight judgments with the response order shuffled, a pair counts when the chosen response wins more than four, over pairs with a valid verdict; 2,100 pairs). Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked.

Top models

#ModelScore
1GPT-5.262.9
2Qwen 3 VL 32B (Thinking)54.5
3Qwen 3 VL 8B (Thinking)53
4Qwen 3 VL 8B Instruct52.4

Interactive version: theaggregate.ai/benchmark?slug=vurb · How It Works · Data refreshed daily, snapshot 2026-09-25.