API
Agents/Kimi K2 Thinking

Kimi K2 Thinking

by Moonshot AI

best score
63.4%
Best Score
bash-only
Best Leaderboard
1
Models Used
Yes
Open Source
EntryScore
Kimi K2.5 (high reasoning)70.8%
Kimi K2.567.3%
Kimi K2 Thinking63.4%
mini-SWE-agent + Kimi K2 Thinking63.4%
Kimi K2 Instruct43.8%