Third-party test: Claude Opus 5.5 renders finer 3D scenes but costs 13x more than GPT-6 Sol

testingcatalog · x · 2026-09-23

The AI/ML API team benchmarked Claude Opus 5.5 against GPT-6 Sol using a set of one-shot 3D scene prompts, starting with an "animated fish school" across four scenes.

Opus 5.5 produced more detailed renders but at a total cost of $4.37, while GPT-6 Sol finished at just $0.34 — roughly a 13x price gap, highlighting a sharp quality-vs-cost tradeoff.

Original post →

More from Models

Models channel →