Gemini 4 Hydrogen lands in Devin, scoring 38.2% on FrontierCode 2.0 behind GPT-6.1 Sol
scaling01 · x · 2026-11-13
Cognition announced that Gemini 4 Hydrogen is now live in Devin Desktop and Devin CLI.
On FrontierCode 2.0, a benchmark evaluating models on real-world engineering tasks by quality and mergeability, Gemini 4 Hydrogen scores 38.2%, just behind GPT-6.1 Sol. The accompanying score-vs-cost chart shows it roughly matching GPT-6.1 Sol at lower cost, while Fable 5.2 (49%) and Opus 5.5 lead overall; Gemini 4 Carbon sits near 32%, with mid-cost models like Haiku 5.5 and SWE-2 Flash in the 20-30% band.
More from coding & agent
- Visual AI agents should save discovered pipelines as reusable programs, argues dev — prateekj · 2026-11-13
- AGENTS.md is the ask, not the check: every rule should be backed by a gate — therealdanvega · 2026-11-13
- Rivet: A Design Agent That Explores Dozens of UI Directions in Parallel for Your Coding Agent — floguo · 2026-11-13
- Letting Claude loose on ancestry data produced surprisingly wild results — D3VAUX · 2026-11-13
- Script in, film out: Claude Fable 5.2 makes a full trailer via Higgsfield MCP — techhalla · 2026-11-13
- Salesforce's A²-Bench: 500 scenarios expose 20 failure modes in multi-agent teamwork — mohitban47 · 2026-11-13