On SWE-Bench Verified, the model achieved a score of 70.6%. This performance is notably competitive when placed alongside significantly larger models; it outpaces DeepSeek-V3.2, which scores 70.2%, ...
Kimi K2.5 handles up to 100 sub-agents and 1,500 tool calls, cutting task time 4.5x so you finish complex work sooner.
Autonomous AI agents are creating a new identity blind spot as they operate outside traditional IAM controls. Token Security ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results