Every AI leaderboard

28 leaderboards · 986 models ranked

Moonshot AI vs Microsoft

Each lab shows its best-ranked model on every board. One row per board where at least one is ranked, from each board's current capture.

  • Moonshot AI
  • Microsoft

Head to head on 2 boards: Moonshot AI places best on 2 and Microsoft places best on 0. Both ranked on 2 of 25 boards.

BoardMoonshot AIMicrosoft
Chat2
MultiChallengeScoreyesterday#1561.4%Kimi K2.5
Text ArenaArena ratingyesterday#161,488Kimi K3
Reasoning7
MMLU-ProAccuracy · staleyesterday#5681.0%best of the pickedKimi K2 Thinking#7576.0%Phi 4 Plus
AA IntelligenceIndexyesterday#1046.5Kimi K3.1 Pro
GPQA DiamondAccuracyyesterday#1194.2%Kimi K3.1 Pro Together
LiveBenchGlobal averageyesterday#1479.2%Kimi K3
HLEAccuracyyesterday#1724.4%Kimi K2.5
Epoch ECIECIyesterday#21158.5Kimi K3
ARC-AGI-2Scoreyesterday#3560.4%Kimi K3
Coding4
SWE-Bench ProResolvedyesterday#688.2%Kimi K3
WebDev ArenaArena ratingyesterday#91,684Kimi K3.1 Pro
SWE-bench VerifiedResolved · staleyesterday#1070.8%Kimi K2.5
Aider PolyglotPass rate · staleyesterday#1959.1%Kimi K2 Thinking
Agents and tools2
BFCLOverall accuracy · staleyesterday#959.1%best of the pickedMoonshotai Kimi K2#5028.8%Phi 4
MCP AtlasPass rateyesterday#1182.3%Kimi K3
Vision2
Document ArenaArena ratingyesterday#291,451Kimi K2.6
Vision ArenaArena ratingyesterday#331,264Kimi K2.6
Image2
Image EditArena ratingyesterday#41,467MAI Image 2.7
Text-to-ImageArena ratingyesterday#61,330MAI Image 2.6
Speech2
Open ASRAverage WERyesterday#35.55 WERazure-speech-09-2026 (microsoft)
Speech ArenaArena ratingyesterday#311,145Azure Hd 2.5
Embeddings1
MTEBMean task scoreyesterday#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedyesterday#636 tok/sKimi K3.1 Pro
Price1
AA PriceBlended priceyesterday#10$4.00Kimi K3.1 Pro
Usage1
OpenRouterWeekly tokensyesterday#84.4T tokKimi K3.1 Pro

Green marks the best placing among the picked where two or more are ranked; ties are marked for each. Ranks are each board's own order (lower is better), scores as the board published them. Dash: not on that board.

More comparisons