Every AI leaderboard

28 leaderboards · 986 models ranked

DeepSeek vs OpenAI vs Microsoft vs Xiaomi

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.

  • DeepSeek
  • OpenAI
  • Microsoft
  • Xiaomi

Head to head on 20 boards: OpenAI places best on 15, DeepSeek places best on 2, Microsoft places best on 2 and Xiaomi places best on 1. All 4 ranked on 0 of 27 boards.

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

BoardDeepSeekOpenAIMicrosoftXiaomi
Chat2
Text ArenaArena ratingyesterday#321,475DeepSeek V4.1 Flash#191,485best of the pickedGPT-5.6 Sol#261,479MiMo-V2.6-Pro
MultiChallengeScoreyesterday#574.9%DeepSeek V4P1 Flash#182.0%best of the pickedGPT-6.1 Sol
Reasoning7
AA IntelligenceIndexyesterday#1632.6DeepSeek V4.1 Flash#356.9best of the pickedGPT-6 Astra#2029.9MiMo-V2.6-Pro
MMLU-ProAccuracy · staleyesterday#3385.0%DeepSeek-V3.2#389.3%best of the pickedo1#7576.0%Phi 4 Plus
Epoch ECIECIyesterday#19159.3DeepSeek V4.1 Flash#1169.1best of the pickedGPT-6 Astra
ARC-AGI-2Scoreyesterday#1978.1%DeepSeek V4.1 Flash#195.0%best of the pickedGPT-6 Astra
GPQA DiamondAccuracyyesterday#2193.2%DeepSeek V4.1 Flash#295.8%best of the pickedGPT-6 Astra
LiveBenchGlobal averageyesterday#881.1%DeepSeek V4.1 Flash#482.2%best of the pickedGPT-6 Astra
HLEAccuracyyesterday#154.8%GPT-6 Astra
Coding4
WebDev ArenaArena ratingyesterday#141,665DeepSeek V4.1 Flash#31,770best of the pickedGPT-6 Astra#201,636MiMo-V2.6-Flash
Aider PolyglotPass rate · staleyesterday#874.2%DeepSeek-V3.2#188.0%best of the pickedGPT-5
SWE-bench VerifiedResolved · staleyesterday#1170.0%DeepSeek-V3.2#672.8%best of the pickedGPT-5.2
SWE-Bench ProResolvedyesterday#490.2%GPT-6 Astra
Agents and tools3
BFCLOverall accuracy · staleyesterday#1256.7%DeepSeek-V3.2#763.0%best of the pickedo3#5028.8%Phi 4
Search ArenaArena ratingyesterday#11,255GPT-5.6 Sol
MCP AtlasPass rateyesterday#1481.8%GPT-5.6
Vision2
Vision ArenaArena ratingyesterday#341,263DeepSeek V4.1 Flash#81,293best of the pickedGPT-6.1 Sol#481,248MiMo-V2.6-Flash
Document ArenaArena ratingyesterday#51,486GPT-5.6 Sol
Image2
Text-to-ImageArena ratingyesterday#11,429best of the pickedGPT Image 2.5 Sunburst#61,330MAI Image 2.6
Image EditArena ratingyesterday#11,517best of the pickedGPT Image 2.5 Sunburst#41,467MAI Image 2.7
Video1
Text-to-VideoArena ratingyesterday#131,367Sora 2 Pro
Speech2
Speech ArenaArena ratingyesterday#421,107TTS 1 Hd#311,145best of the pickedAzure Hd 2.5#681,052MiMo V2.5 TTS
Open ASRAverage WERyesterday#186.80 WERgpt-transcribe (openai)#35.55 WERbest of the pickedazure-speech-09-2026 (microsoft)
Embeddings1
MTEBMean task scoreyesterday#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedyesterday#1323 tok/sDeepSeek V4 Pro 0813#1522 tok/sGPT-6.1 Sol#164 tok/sbest of the pickedMiMo-V2.6-Flash
Price1
AA PriceBlended priceyesterday#3$0.53best of the pickedDeepSeek V4.1 Flash#6$2.00GPT-6.1 Terra
Usage1
OpenRouterWeekly tokensyesterday#156.0T tokbest of the pickedDeepSeek V4.1 Flash#47.2T tokGPT-6 Luna

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