Same 3D prompt run through 8 models for comparison

After Mistral Large 4 launched, the author ran the same 3D prompt through 8 models, including GPT-6 Astra, GPT-6.1 Sol and Opus 5.5, with one shot and no fixes.

Dominique Silvestre

@domsilvestreArchived 27 days agoOriginally posted 2026.10.07

Dominique Silvestre @domsilvestreOriginally posted 2026.10.07

Open original on X

Mistral just shipped Large 4, its biggest model ever. So I gave the same 3D prompt to 8 models. One shot, no fixes. Open: Mistral Large 4, Kimi K3, GLM 5.3, DeepSeek V4 Pro Closed: Claude Opus 5.5, Sonnet 5.5, GPT-6 Astra, GPT-6.1 Sol Results below 👇

x.com/domsilvestre/status/2107567209035833402Archived 2026.10.07 10:10

Open original on X