π Kimi-K2.7-Code, our latest coding model, is now released and open-sourced!
π· Improved coding & agent performance over K2.6: +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite.
π· Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6.
π· Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates.
β‘οΈ 6x High-Speed Mode coming soon!
π Available today via Kimi API and Kimi Code.
π Kimi Code: https://t.co/uvoSJKyGCY
π API: https://t.co/EOZkbOwCN4
π DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length.
πΉ DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models.
πΉ DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice.
Try it now at https://t.co/GCdiMzk1Dl via Expert Mode / Instant Mode. API is updated & available today!
π Tech Report: https://t.co/drlDrxkYtp
π€ Open Weights: https://t.co/T13Y8i7SDM
1/n
Paper: https://t.co/FHAWM26E1c
Code: https://t.co/IwEhuUSZVJ
Blog: https://t.co/GgcQUctmfZ
https://t.co/3jW3BCUZni
As usual, Mamba models can be applied to any modality. We focused on language modeling, where it dominates its predecessor Mamba-2 as well as other commonly used linear models.