KVBench (Detailed Caption) - History (Chinese): leaderboard
Metric: Checklist score (%) on the history 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.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Seedream-4.0 | 28.67 |
| 2 | GPT-Image (KVBench checkpoint unspecified) | 25.86 |
| 3 | Qwen-Image | 17.13 |
| 4 | Z-Image | 16.55 |
| 5 | Nano Banana Pro (Gemini 3 Pro Image) | 11.5 |
| 6 | FLUX.2-dev | 10.25 |
| 7 | Gemini 2.5 Flash Image | 9.37 |
| 8 | Show-o2 | 3.69 |
| 9 | HiDream (KVBench checkpoint unspecified) | 2.87 |
| 10 | FLUX.1-dev | 2.87 |
Interactive version: theaggregate.ai/benchmark?slug=kvbench-detailed-caption-history-chinese · How It Works · Data refreshed daily, snapshot 2026-10-07.