Blender watch test: DeepSeek does it for $0.80 vs Claude Fable's $119
HankYeomans · x · 2026-11-16
Developer ivanfioravanti benchmarked multiple models on a 3D "Mechanical Watch" Blender modeling task, comparing time and cost:
- DeepSeek V4.1 Flash: finished in 3h16m at just $0.80 ($0 running locally), but the renders show scattered, misassembled parts
- Claude Sonnet 5.5: 5h46m, $44.24, fairly complete structure
- Claude Opus 5.5: 8h30m, $73.48
- Claude Fable 5.2: 5h29m at $119.02, the priciest — with the most refined, realistic gear-train details
- Kimi K3.1 Pro and Claude Haiku 5.5 still building
Takeaway: Anthropic models "play in another league" for Blender work, with quality-cost gaps of over 100x.
More from Models
- Anthropic user blasts its 'queuing steering' system as awful — willdepue · 2026-11-16
- Rumor: Google Prepping Strongest Gemini Model Yet, Codenamed Krypton — aziz4ai · 2026-11-16
- Users say Gemini turned colder after Nov 12 update, want old version back — Sean8277 · 2026-11-16
- Claude Code auto-memory injects context into every tool call; dev says disable it — nateberkopec · 2026-11-16
- Scaling曲线新假说:三段S曲线接力,外推天花板或达178+ — scaling01 · 2026-11-16
- Grok rewrite reportedly degrades at understanding writing intent — xiaosun86 · 2026-11-16