Kimi-K2.7-Code 开源编程模型发布，基准测试最高提升31.5%，推理token消耗降低30%
英文摘要
Kimi released and open-sourced Kimi-K2.7-Code, their latest coding model. It improves coding and agent performance over K2.6: +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, +31.5% on MLS Bench Lite. Reasoning efficiency is enhanced with 30% lower reasoning-token usage compared to K2.6. The model shows better instruction following and higher end-to-end coding task success rates. A 6x High-Speed Mode is planned for future release. The model is available now via Kimi API and Kimi Code.
中文摘要
Kimi 发布了开源编程模型 Kimi-K2.7-Code。该模型在编程和智能体性能上较 K2.6 全面提升：Kimi Code Bench v2 提升21.8%，Program Bench 提升11.0%，MLS Bench Lite 提升31.5%。推理效率得到优化，推理token消耗较K2.6减少30%。模型在长周期编程任务中指令遵循和端到端成功率更高。6倍高速模式即将推出。现已通过 Kimi API 和 Kimi Code 可用。
关键要点
Kimi-K2.7-Code is open-sourced and available via API and Kimi Code platform.
Kimi-K2.7-Code 已开源，可通过 API 和 Kimi Code 使用。
Benchmark gains over K2.6: Kimi Code Bench v2 +21.8%, Program Bench +11.0%, MLS Bench Lite +31.5%.
相比 K2.6 基准测试提升：Kimi Code Bench v2 +21.8%，Program Bench +11.0%，MLS Bench Lite +31.5%。
Reasoning token consumption reduced by 30% versus K2.6, reducing overthinking.
推理token消耗较 K2.6 降低30%，减少过度思考。
Improved long-horizon coding: better instruction following and higher end-to-end task success rates.
长周期编程任务改进：指令遵循更强，端到端任务成功率更高。
A 6x High-Speed Mode will be released soon.
即将推出6倍高速模式。