gpt-6VIDEO
Blender Bench v1: benchmark tests frontier LLMs on 3D workflows
A new benchmark tests frontier LLMs on 20 realistic 3D production workflows; GPT-6 Astra leads overall, while Claude Opus 5.5 wins modeling and cloth simulation.
Refresh
@refresh_devArchived 2026.10.01Originally posted 2026.10.01
Refresh @refresh_devOriginally posted 2026.10.01
Introducing Blender Bench v1 (BBv1): a benchmark for frontier LLMs on 20 realistic 3D production workflows including animation, modeling, rigging, cloth & surfacing. GPT-6 Astra leads overall; Claude Opus 5.5 wins modeling & cloth simulation.
x.com/refresh_dev/status/2105359734287249559Archived 2026.10.01 10:11