Gemini 3.7 Flash ties SOTA; CAD Agent bottleneck is integration
jakedahn · x · 2026-08-23
Jake Dahn notes that Google DeepMind's Gemini 3.7 Flash tied for first place in a CAD (Fusion 360) computer use benchmark with 24% accuracy. This suggests the bottleneck isn't the model itself, but rather the Harness/MCP integration. The gap between the "best" and "cheapest-good-enough" models for CAD is near zero, significantly impacting who can build agents in Fusion 360.
Related event: CADBench: Gemini 3.7 Flash Ties for First, But Top Pass Rate Only 24.6%(3 posts)→
More from coding & agent
- Developer rebuilds GitHub in 4 days: Keel makes agents declare intent before changing code — threepointone · 2026-10-16
- Stop using small models as judges with overloaded context, dev warns — xeophon · 2026-10-16
- Meta's open-weight Muse Spark Open hits Ollama with 1M-token context and Claude Code support — ollama · 2026-10-16
- Monid launches: one balance, pay-per-call access to 1,700+ tools for AI agents — HeyAmit_ · 2026-10-16
- OpenAI publishes Sites tutorial: build and share your first Site — OpenAIDevs · 2026-10-16
- OpenAI Sites goes GA for Enterprise with US/EU data residency — OpenAIDevs · 2026-10-16