UniG2U-Bench (Direct) - Real-world Applications: leaderboard
Metric: Accuracy (%) on the 200 real-world application items (attentional focusing and visual shortest-path), mean of the two subtask accuracies, from UniG2U-Bench, answering directly from the image and question in one pass (no intermediate image), greedy decoding; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 28 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 45.25 | #333 |
| 2 | Qwen 2.5 VL 7B | 40.25 | #627 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=unig2u-bench-direct-real-world-applications · How It Works · Data refreshed daily, snapshot 2026-10-11.