UniG2U-Bench (Direct): leaderboard
Metric: Accuracy (%) over the 3,000 UniG2U-Bench image questions (200 real-world application, 200 geometry, 200 physics, 537 puzzle and game, 100 chart, 500 spatial-intelligence and 1,263 perception items curated from VSP, RealUnify, Geometry3K, AuxSolidMath, PhyX, Uni-MMMU, BabyVision, ChartQA, MMSI-Bench, IllusionBench and VisualPuzzles), micro-averaged over items, 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 | 38.96 | #333 |
| 2 | Qwen 2.5 VL 7B | 34.45 | #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 · How It Works · Data refreshed daily, snapshot 2026-10-11.