Kimi K3 Is Now Available in Devin
Cognition has made Kimi K3 available in Devin Desktop and Devin CLI. On FrontierCode 1.1, Cognition's own benchmark that grades models on real world engineering tasks by quality and mergeability, Kimi K3 is approaching frontier level performance. It surpasses GPT-5.5 and falls only behind Opus, Fable, and GPT-5.6 Sol, making it the only open source model that reaches this level. Cognition says Kimi K3 is especially strong at debugging, because it discovers ground truth by running code instead of assuming or pattern matching, and it often reproduces a bug on its own before editing any files. The honest tradeoff: Cognition also reports that Kimi K3 falls short on spec adherence and sometimes deviates from stated specs, an area where GPT-5.6 Sol, Opus 5, and Fable 5 do better.
Transcript
Cognition says Kimi K3 is now available in Devin, and it is approaching frontier level coding performance.
Cognition added Kimi K3 to Devin Desktop and Devin CLI. The open source model is now live inside both products.
On Cognition's FrontierCode benchmark, Kimi K3 surpasses GPT-5.5 and falls behind only Opus, Fable, and GPT-5.6 Sol. It is the only open source model at that level.
Cognition says Kimi K3 is strong at debugging and runs code to find the real problem. It deviates from stated specifications sometimes.
Inboxsmith helps small businesses handle calls and messages so nothing gets missed. Please like and subscribe for more news.
Sources
Every claim in this video comes from the top ranking coverage of this topic. The claims and where each one came from:
- Kimi K3 is live in Devin Desktop and Devin CLI.(Cognition official announcement)
- On FrontierCode 1.1, Kimi K3 is approaching frontier level performance and surpasses GPT-5.5.(Cognition official announcement)
- Kimi K3 falls only behind Opus, Fable, and GPT-5.6 Sol on FrontierCode 1.1.(Cognition official announcement)
- Kimi K3 is the only open source model that achieves this level of performance.(Cognition official announcement)
- Kimi K3 excels at debugging and discovers ground truth by running code rather than assuming or pattern matching.(Cognition official announcement)
- Kimi K3 falls short in spec adherence and deviates from stated specs sometimes.(Cognition official announcement)