KVBench (Brief Caption) - Math (Chinese): leaderboard
Metric: Checklist score (%) on the math 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) | 41.29 |
| 2 | OmniGen2 | 36.31 |
| 3 | Seedream-4.0 | 35.6 |
| 4 | GPT-Image (KVBench checkpoint unspecified) | 29.33 |
| 5 | FLUX.2-dev | 28.27 |
| 6 | FLUX.2-max | 24.89 |
| 7 | Show-o2 | 23.56 |
| 8 | FLUX.1-Krea-dev | 21.02 |
| 9 | FLUX.1-dev | 20.93 |
| 10 | SD3.5-Large (KVBench GGUF build, quantization unspecified) | 20.49 |
Interactive version: theaggregate.ai/benchmark?slug=kvbench-brief-caption-math-chinese · How It Works · Data refreshed daily, snapshot 2026-10-07.