Every AI leaderboard

28 leaderboards · 986 models ranked

Moonshot AI vs OpenAI vs DeepSeek vs Google

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
  • OpenAI
  • DeepSeek
  • Google

Head to head on 26 boards: OpenAI places best on 12, Google places best on 11, DeepSeek places best on 2 and Moonshot AI places best on 1. All 4 ranked on 15 of 28 boards.

Two at a time on this screen. Tap one to swap it in.

BoardMoonshot AIOpenAIDeepSeekGoogle
Chat2
Text ArenaArena ratingyesterday#161,488Kimi K3#191,485GPT-5.6 Sol#321,475DeepSeek V4.1 Flash#11,526best of the pickedGemini 4 Carbon
MultiChallengeScoreyesterday#1561.4%Kimi K2.5#182.0%best of the pickedGPT-6.1 Sol#574.9%DeepSeek V4P1 Flash#278.7%Gemini 4 Argon
Reasoning7
AA IntelligenceIndexyesterday#1046.5Kimi K3.1 Pro#356.9GPT-6 Astra#1632.6DeepSeek V4.1 Flash#160.0best of the pickedGemini 4 Carbon
GPQA DiamondAccuracyyesterday#1194.2%Kimi K3.1 Pro Together#295.8%GPT-6 Astra#2193.2%DeepSeek V4.1 Flash#196.4%best of the pickedGemini 4 Argon
Epoch ECIECIyesterday#21158.5Kimi K3#1169.1best of the pickedGPT-6 Astra#19159.3DeepSeek V4.1 Flash#6166.4Gemini 4 Argon
ARC-AGI-2Scoreyesterday#3560.4%Kimi K3#195.0%best of the pickedGPT-6 Astra#1978.1%DeepSeek V4.1 Flash#591.3%Gemini 4 Argon
MMLU-ProAccuracy · staleyesterday#5681.0%Kimi K2 Thinking#389.3%o1#3385.0%DeepSeek-V3.2#191.2%best of the pickedGemini 3.1 Pro Preview
LiveBenchGlobal averageyesterday#1479.2%Kimi K3#482.2%best of the pickedGPT-6 Astra#881.1%DeepSeek V4.1 Flash#1578.8%Gemini 3.7 Flash
HLEAccuracyyesterday#1724.4%Kimi K2.5#154.8%best of the pickedGPT-6 Astra#346.4%Gemini 3.1 Pro Preview
Coding4
Aider PolyglotPass rate · staleyesterday#1959.1%Kimi K2 Thinking#188.0%best of the pickedGPT-5#874.2%DeepSeek-V3.2#383.1%Gemini 2.5 Pro (Jun 2025)
SWE-bench VerifiedResolved · staleyesterday#1070.8%Kimi K2.5#672.8%GPT-5.2#1170.0%DeepSeek-V3.2#275.8%best of the pickedGemini 3 Flash
WebDev ArenaArena ratingyesterday#91,684Kimi K3.1 Pro#31,770best of the pickedGPT-6 Astra#141,665DeepSeek V4.1 Flash#41,767Gemini 4 Carbon
SWE-Bench ProResolvedyesterday#688.2%Kimi K3#490.2%GPT-6 Astra#392.2%best of the pickedGemini 4 Argon
Agents and tools3
BFCLOverall accuracy · staleyesterday#959.1%Moonshotai Kimi K2#763.0%o3#1256.7%DeepSeek-V3.2#372.5%best of the pickedGemini 3 Pro
MCP AtlasPass rateyesterday#1182.3%Kimi K3#1481.8%GPT-5.6#190.7%best of the pickedGemini 4 Argon
Search ArenaArena ratingyesterday#11,255best of the pickedGPT-5.6 Sol#141,208Gemini 3.1 Pro Preview
Vision2
Vision ArenaArena ratingyesterday#331,264Kimi K2.6#81,293GPT-6.1 Sol#341,263DeepSeek V4.1 Flash#61,294best of the pickedGemini 3.7 Flash
Document ArenaArena ratingyesterday#291,451Kimi K2.6#51,486best of the pickedGPT-5.6 Sol#161,469Gemini 3.8 Flash
Image2
Text-to-ImageArena ratingyesterday#11,429best of the pickedGPT Image 2.5 Sunburst#71,325Gemini Nano Banana 2.1
Image EditArena ratingyesterday#11,517best of the pickedGPT Image 2.5 Sunburst#81,427Gemini Nano Banana 2.1
Video2
Text-to-VideoArena ratingyesterday#131,367Sora 2 Pro#11,541best of the pickedGemini Omni 1.2 Flash
Image-to-VideoArena ratingyesterday#11,502Gemini Omni 1.2 Flash
Speech2
Speech ArenaArena ratingyesterday#421,107TTS 1 Hd#61,283best of the pickedGemini 3.8 Flash TTS
Open ASRAverage WERyesterday#186.80 WERbest of the pickedgpt-transcribe (openai)#5813.20 WERgemma-4-E4B-it (google)
Embeddings1
MTEBMean task scoreyesterday#568.4%gemini-embedding-001 (google)
Speed1
AA SpeedOutput speedyesterday#636 tok/sbest of the pickedKimi K3.1 Pro#1522 tok/sGPT-6.1 Sol#1323 tok/sDeepSeek V4 Pro 0813#735 tok/sGemini 4 Carbon
Price1
AA PriceBlended priceyesterday#10$4.00Kimi K3.1 Pro#6$2.00GPT-6.1 Terra#3$0.53best of the pickedDeepSeek V4.1 Flash#5$1.50Gemini 3.8 Flash
Usage1
OpenRouterWeekly tokensyesterday#84.4T tokKimi K3.1 Pro#47.2T tokGPT-6 Luna#156.0T tokbest of the pickedDeepSeek V4.1 Flash

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