BLENDER-BENCH
~ same prompt, different LLM — every model gets the same brief in Blender, you judge the render ~
Google / Gemini 3.8 Flash / thinking:medium has entered the arena NEW!
[ << prev | the LLM-eval webring | next >> ] · sign our guestbook
Votes cast on this bench: 001671 · 163 runs · 26 contestants