KVBench (Brief Caption) - Chemistry (Chinese): leaderboard
Metric: Checklist score (%) on the chemistry 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) | 70.67 |
| 2 | Seedream-4.0 | 54.35 |
| 3 | GPT-Image (KVBench checkpoint unspecified) | 50.5 |
| 4 | FLUX.2-dev | 37 |
| 5 | FLUX.2-max | 33.42 |
| 6 | FLUX.1-dev | 21.82 |
| 7 | Z-Image | 21.25 |
| 8 | BAGEL-7B-MoT | 18.73 |
| 9 | OmniGen2 | 18.25 |
| 10 | FLUX.1-Krea-dev | 17.3 |
Interactive version: theaggregate.ai/benchmark?slug=kvbench-brief-caption-chemistry-chinese · How It Works · Data refreshed daily, snapshot 2026-10-07.