Unison - Generation-Guided Understanding: leaderboard
The generation-guided understanding score of Unison (2026), a benchmark for unified multimodal models: answering a question that is solved by generating an intermediate image, as a unified percent score from the Unison-Judge and task metrics. Higher is better.
Metric: Unified score (%) on the generation-guided understanding dimension of Unison (2,169 unified understanding-and-generation samples): answer a question that is solved by generating an intermediate image, scored by the authors' Unison-Judge (a human-aligned 8B judge) and task metrics; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 52.7 | #176 |
| 2 | Gemini 3 Pro | 43.9 | #137 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=unison-generation-guided-understanding · How It Works · Data refreshed daily, snapshot 2026-11-13.