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

KVBench (2026) tests whether text-to-image models can draw correct senior high-school physics 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 physics 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
1FLUX.1-dev50.4
2GPT-Image (KVBench checkpoint unspecified)42.2
3Seedream 4.039.53
4FLUX.2-dev39.13
5Nano Banana Pro (Gemini 3 Pro Image)37.2
6FLUX 2 Max35.07
7BAGEL-7B-MoT29.67#4668
8SD3.5-Large (KVBench GGUF build, quantization unspecified)28.73
9Qwen-Image28
10Janus-Pro26.33
11OmniGen226.07#4625
12Show-o223.73
13Z-Image20
14FLUX.1-Krea-dev18.73

Interactive version: theaggregate.ai/benchmark?slug=kvbench-brief-caption-physics-english · How It Works · Data refreshed daily, snapshot 2026-11-22.