KVBench (Brief Caption) - Geography (Chinese): leaderboard
Metric: Checklist score (%) on the geography prompts in Chinese, each given as a brief caption, so the model must supply the textbook knowledge itself: KVBench knowledge-intensive text-to-image prompts from over 30 senior high-school textbooks (150 per subject and language, each with a textbook reference image); Qwen2.5-VL-32B-Instruct answers a checklist of four to six binary questions (key objects, attributes, spatial relations, reasoning outcomes) about each generated image, and the score is the mean share of satisfied items, in percent; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Nano Banana Pro (Gemini 3 Pro Image) | 63.29 |
| 2 | Seedream-4.0 | 52.29 |
| 3 | FLUX.2-dev | 49.62 |
| 4 | GPT-Image (KVBench checkpoint unspecified) | 44.31 |
| 5 | FLUX.2-max | 31.96 |
| 6 | Qwen-Image | 29 |
| 7 | BAGEL-7B-MoT | 27.91 |
| 8 | Z-Image | 27.33 |
| 9 | OmniGen2 | 27.13 |
| 10 | FLUX.1-dev | 25.51 |
Interactive version: theaggregate.ai/benchmark?slug=kvbench-brief-caption-geography-chinese · How It Works · Data refreshed daily, snapshot 2026-10-07.