KVBench (Detailed Caption) - Chemistry (Chinese): leaderboard
KVBench (2026) tests whether text-to-image models can draw correct senior high-school chemistry content, such as diagrams and scientific illustrations, from Chinese prompts given as a detailed caption that spells out the required visual content. Qwen2.5-VL-32B checks each image against a list of textbook-grounded constraints; the score is the percentage satisfied, higher is better.
Metric: Checklist score (%) on the chemistry prompts in Chinese, each given as a detailed caption that spells out the required visual content: 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. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Nano Banana Pro (Gemini 3 Pro Image) | 82.95 | |
| 2 | GPT-Image (KVBench checkpoint unspecified) | 54.09 | |
| 3 | Seedream 4.0 | 50.32 | |
| 4 | Gemini 2.5 Flash Image | 39.01 | |
| 5 | FLUX.2-dev | 33.06 | |
| 6 | Qwen-Image | 31.01 | |
| 7 | Z-Image | 30.04 | |
| 8 | FLUX 2 Max | 24.76 | |
| 9 | OmniGen2 | 12.31 | #4579 |
| 10 | HiDream (KVBench checkpoint unspecified) | 11.08 | |
| 11 | BAGEL-7B-MoT | 10.59 | #4619 |
| 12 | Janus-Pro | 9.86 | |
| 13 | FLUX.1-Krea-dev | 8.67 | |
| 14 | SD3.5-Large (KVBench GGUF build, quantization unspecified) | 7.86 | |
| 15 | FLUX.1-dev | 6.21 |
Interactive version: theaggregate.ai/benchmark?slug=kvbench-detailed-caption-chemistry-chinese · How It Works · Data refreshed daily, snapshot 2026-11-21.