← All benchmarks

Bronze Age Comic Panel — Superhero Landing

Three AI models try to render a 1975-82 Bronze Age comic panel — Benday halftones, period-authentic CMYK newsprint palette, speech bubble with bold serif lettering, KRA-THOOM sound effect. Stress-tests text rendering (speech bubble + sound effect), period-style adherence (halftones not modern gradients), and dynamic-anatomy in a single fixed frame.

8 models compared · same input · same prompt

Run it on your idea

Run your own prompt across all 8 models

Don’t just compare ours — get every model’s take on your idea, side by side. Full-res, one click. No juggling 8 accounts.

Input & prompt

Prompt template

A single Bronze Age comic-book panel: a superhero landing dramatically. The model invents the scene, the speech bubble's words, the sound effect, the framing. The test is whether the model has the Bronze Age visual vocabulary — not a modern digital comic.

ChatGPT (GPT Image 2)

Try this →
65.1sopenai/gpt-image-2

Grok Imagine Pro

Try this →
13.3sx-ai/grok-imagine-image-pro

Nano Banana 2 (Gemini)

Try this →
14.6sgoogle/nano-banana-2

Flux Kontext Pro

Try this →

Qwen Image 2.0 Pro

Try this →

Seedream 5 Lite

Try this →

Nano Banana Pro

Try this →

FLUX.2 Max

Try this →

Want to try this with your own twist?

Run the same prompt with your own variables — it's free.

Try the prompt →

New benchmark every week

We put the latest models head to head on the same brief — no labels, you judge. Get each new benchmark in your inbox the morning it drops.