-
Overall rank
-
Podium score
0
Board wins
Apr 20, 2026
Released
Chat
Which model people prefer in blind head-to-head conversations.
Reasoning
Hard questions with checkable answers: science, math, puzzles, expert exams.
Coding
Fixing real repositories, building web apps, editing code.
Vision
Understanding images, charts and documents.
More from Moonshot AI
Kimi K3Kimi K2.5Moonshotai Kimi K2Kimi K2.7 CodeKimi K2P5Kimi K2 TurboKimi K2 ThinkingKimi K2.5 Instant
Scores as published by each board on the capture date. Model names and logos belong to their owners; logos via logo.dev.