KVBench (Brief Caption) - Geography (English): leaderboard

KVBench (2026) tests whether text-to-image models can draw correct senior high-school geography content, such as diagrams and scientific illustrations, from English prompts given as a brief caption, so the model must supply the textbook knowledge itself. 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 geography prompts in English, 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. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-Image (KVBench checkpoint unspecified)45.96
2FLUX.2-dev41.56
3SD3.5-Large (KVBench GGUF build, quantization unspecified)38.44
4Seedream 4.037.87
5Qwen-Image27.87
6FLUX.1-dev22.49
7BAGEL-7B-MoT19.07#4619
8FLUX 2 Max18.71
9FLUX.1-Krea-dev18.58
10OmniGen218.53#4579
11Janus-Pro18.49
12Z-Image16.04
13Show-o215.11
14Nano Banana Pro (Gemini 3 Pro Image)14

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