Devin adds Gemini 4 Neon support
Cognition has integrated Google's Gemini 4 Neon model into Devin Desktop and Devin CLI. Internal evaluations on FrontierCode 2.0 demonstrate that the model achieves parity with frontier models on pull request mergeability while offering faster iteration speeds.
Devin's shift toward Gemini 4 Neon highlights how autonomous coding agents are prioritizing throughput and cost efficiency alongside raw reasoning.
- –While heavy reasoning models deliver high PR mergeability, their latency bogs down iterative agent loops; Neon offers a faster alternative without sacrificing code quality.
- –Matching frontier models on FrontierCode 2.0 proves that specialized, efficient architectures can handle complex repository maintenance when guided by robust agent harnesses.
- –Enabling the model across both Devin Desktop and Devin CLI gives engineers flexible model choice for local, terminal-native software engineering.
- –Cognition continues to diversify its model provider backends, preventing single-vendor lock-in and driving down per-task inference costs for developers.
DISCOVERED
1h ago
2026-11-19
PUBLISHED
1h ago
2026-11-19
RELEVANCE
AUTHOR
devindevelopers