Gemini 4 Carbon day-zero test: 44% vs Argon's 21% on coding benchmark
danshipper · x · 2026-11-11
Every's day-zero testing of Google's newly released Gemini 4 Carbon finds it a much better coder than Argon (44% vs 21% on their Senior Engineer benchmark), though still mid-pack. It can work for hours on ambitious builds—a 3D studio-scan model was accurate enough to check gear fit—but doesn't always know when to stop, once doing 15 backlog tasks instead of 6 before being halted after 4.5 hours.
More from Models
- Google launches Gemini 4 Carbon, its strongest frontier model alongside Argon — GeminiApp · 2026-11-11
- Keenable cost breakdown: ~$0.040 per task, 80% from search, on the cost frontier — ArtificialAnlys · 2026-11-11
- Keenable Search 1.0 tops Artificial Analysis Search Index at 83, a third below median cost — ArtificialAnlys · 2026-11-11
- Early access user: Gemini Carbon at frontier, next Google model to rival Fable 5.2 — iruletheworldmo · 2026-11-11
- Dev says AI models refuse to help fix exploits in his own project, switching to Chinese models — AlpinDale · 2026-11-11
- Claude Fable 5.2: 10 Wild One-Prompt Demos in Under 24 Hours — minchoi · 2026-11-11