KVBench (Detailed Caption) - Math (Chinese): leaderboard

KVBench (2026) tests whether text-to-image models can draw correct senior high-school math 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 math 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

#ModelScoreOverall rank
1GPT-Image (KVBench checkpoint unspecified)49.4
2Nano Banana Pro (Gemini 3 Pro Image)47.8
3Seedream 4.044.01
4Z-Image38.13
5Gemini 2.5 Flash Image31.6
6FLUX.2-dev26.87
7FLUX 2 Max17.17
8HiDream (KVBench checkpoint unspecified)14.79
9BAGEL-7B-MoT10.88#4619
10Janus-Pro10.57
11FLUX.1-Krea-dev9.99
12SD3.5-Large (KVBench GGUF build, quantization unspecified)9.44
13Show-o29.16
14Qwen-Image8.59
15FLUX.1-dev8.12

Interactive version: theaggregate.ai/benchmark?slug=kvbench-detailed-caption-math-chinese · How It Works · Data refreshed daily, snapshot 2026-11-21.