OmniClean - WorldSense: leaderboard
Metric: Accuracy (%; the 875 of 3,172 WorldSense queries left after visual-only cleaning; official answer matching). Source: arxiv.org. Saturation forecast: Around April 2027. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen2.5-Omni-7B | 24.25 |
| 2 | Qwen3 Omni 30B A3B Instruct | 23.79 |
Interactive version: theaggregate.ai/benchmark?slug=omniclean-worldsense · How It Works · Data refreshed daily, snapshot 2026-09-26.