Every AI leaderboard

28 leaderboards · 986 models ranked

Baidu vs Microsoft vs DeepSeek

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.

  • Baidu
  • Microsoft
  • DeepSeek

Head to head on 4 boards: DeepSeek places best on 4, Baidu places best on 0 and Microsoft places best on 0. All 3 ranked on 1 of 22 boards.

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

BoardBaiduMicrosoftDeepSeek
Chat2
Text ArenaArena ratingyesterday#441,467Ernie 5.1#321,475best of the pickedDeepSeek V4.1 Flash
MultiChallengeScoreyesterday#574.9%DeepSeek V4P1 Flash
Reasoning6
MMLU-ProAccuracy · staleyesterday#6978.4%Ernie 4.5 300b A47B#7576.0%Phi 4 Plus#3385.0%best of the pickedDeepSeek-V3.2
LiveBenchGlobal averageyesterday#881.1%DeepSeek V4.1 Flash
AA IntelligenceIndexyesterday#1632.6DeepSeek V4.1 Flash
Epoch ECIECIyesterday#19159.3DeepSeek V4.1 Flash
ARC-AGI-2Scoreyesterday#1978.1%DeepSeek V4.1 Flash
GPQA DiamondAccuracyyesterday#2193.2%DeepSeek V4.1 Flash
Coding3
Aider PolyglotPass rate · staleyesterday#874.2%DeepSeek-V3.2
SWE-bench VerifiedResolved · staleyesterday#1170.0%DeepSeek-V3.2
WebDev ArenaArena ratingyesterday#141,665DeepSeek V4.1 Flash
Agents and tools2
BFCLOverall accuracy · staleyesterday#5028.8%Phi 4#1256.7%best of the pickedDeepSeek-V3.2
Search ArenaArena ratingyesterday#251,192Ernie 5.1
Vision1
Vision ArenaArena ratingyesterday#671,219ERNIE 5.0 Thinking Preview#341,263best of the pickedDeepSeek V4.1 Flash
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#1323 tok/sDeepSeek V4 Pro 0813
Price1
AA PriceBlended priceyesterday#3$0.53DeepSeek V4.1 Flash
Usage1
OpenRouterWeekly tokensyesterday#156.0T tokDeepSeek 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