Expired50% confidenceBenchmarkExact time
K3 achieved 76.8% on SWE-bench, the best among open-source models, and can run 300 auxiliary agents in parallel.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/28/2026
First Seen
Valid until: 10/12/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedAccording to the documentation, Kimi K2.8 performs at a level comparable to K3 but has more efficient reasoning capabilities, supporting a 1-million-token context window, image and video input, and three reasoning modes: low, high, and max.71% similarUnverifiedThe top open-source models currently at the front of public leaderboards include Moonshot AI's Kimi K3, DeepSeek V4 Pro, Alibaba's Qwen 3.8 Max, and Zhipu AI's GLM 5.3—all developed by domestic Chinese teams.68% similarUnverifiedKimi K3's 2.8 trillion parameter scale surpasses the previously largest open-weight model, DeepSeek-V3, which had 671 billion parameters.67% similarUnverifiedThis demonstration is based on a K8S 1.34.3 cluster deployed with KubeKey 4.0.5.62% similarUnverified以Kimi K3实验，给它预填充1%的Claude Opus解码推理片段，其输出风格就会明显向Opus靠拢，某些区段Claude推理链从Kimi K3提取的容易程度比其他模型高出约6个数量级61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/956007API
curl https://kongchang.com/api/v1/knowledge/claims/956007MCP
get_claim(id=956007)