Every AI leaderboard

Leaderboards28Models ranked986

28 leaderboards · 986 models ranked

Z.ai vs Microsoft vs OpenAI 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.

  • Z.ai
  • Microsoft
  • OpenAI
  • DeepSeek

Head to head on 24 boards: OpenAI places best on 17, Z.ai places best on 4, Microsoft places best on 2 and DeepSeek places best on 2 (a tie counts for each). All 4 ranked on 2 of 27 boards.

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

BoardZ.aiMicrosoftOpenAIDeepSeek
Chat2
Text ArenaArena ratingyesterday#231,482GLM-5.3#191,485best of the pickedGPT-5.6 Sol#321,475DeepSeek V4.1 Flash
MultiChallengeScoreyesterday#182.0%best of the pickedGPT-6.1 Sol#574.9%DeepSeek V4P1 Flash
Reasoning7
MMLU-ProAccuracy · staleyesterday#2986.0%GLM-5#7576.0%Phi 4 Plus#389.3%best of the pickedo1#3385.0%DeepSeek-V3.2
Epoch ECIECIyesterday#29156.9GLM-5.3#1169.1best of the pickedGPT-6 Astra#19159.3DeepSeek V4.1 Flash
ARC-AGI-2Scoreyesterday#2865.8%GLM 5.3 Flash#195.0%best of the pickedGPT-6 Astra#1978.1%DeepSeek V4.1 Flash
GPQA DiamondAccuracyyesterday#2891.9%GLM-5.2#295.8%best of the pickedGPT-6 Astra#2193.2%DeepSeek V4.1 Flash
AA IntelligenceIndexyesterday#1731.7GLM-5.3#356.9best of the pickedGPT-6 Astra#1632.6DeepSeek V4.1 Flash
LiveBenchGlobal averageyesterday#3176.1%GLM-5.3#482.2%best of the pickedGPT-6 Astra#881.1%DeepSeek V4.1 Flash
HLEAccuracyyesterday#288.3%GLM-4p5#154.8%best of the pickedGPT-6 Astra
Coding4
WebDev ArenaArena ratingyesterday#251,621GLM-5.3#31,770best of the pickedGPT-6 Astra#141,665DeepSeek V4.1 Flash
SWE-bench VerifiedResolved · staleyesterday#672.8%best of the pickedGLM-5#672.8%best of the pickedGPT-5.2#1170.0%DeepSeek-V3.2
Aider PolyglotPass rate · staleyesterday#188.0%best of the pickedGPT-5#874.2%DeepSeek-V3.2
SWE-Bench ProResolvedyesterday#1184.3%GLM-5.3#490.2%best of the pickedGPT-6 Astra
Agents and tools3
BFCLOverall accuracy · staleyesterday#472.4%best of the pickedGLM 4.6#5028.8%Phi 4#763.0%o3#1256.7%DeepSeek-V3.2
MCP AtlasPass rateyesterday#884.2%best of the pickedGLM-5.3#1481.8%GPT-5.6
Search ArenaArena ratingyesterday#11,255GPT-5.6 Sol
Vision2
Vision ArenaArena ratingyesterday#291,272GLM 5.3 Flash#81,293best of the pickedGPT-6.1 Sol#341,263DeepSeek V4.1 Flash
Document ArenaArena ratingyesterday#401,407GLM-5v Turbo#51,486best of the pickedGPT-5.6 Sol
Image2
Text-to-ImageArena ratingyesterday#661,012GLM Image#61,330MAI Image 2.6#11,429best of the pickedGPT Image 2.5 Sunburst
Image EditArena ratingyesterday#41,467MAI Image 2.7#11,517best of the pickedGPT Image 2.5 Sunburst
Video1
Text-to-VideoArena ratingyesterday#131,367Sora 2 Pro
Speech2
Open ASRAverage WERyesterday#35.55 WERbest of the pickedazure-speech-09-2026 (microsoft)#186.80 WERgpt-transcribe (openai)
Speech ArenaArena ratingyesterday#311,145best of the pickedAzure Hd 2.5#421,107TTS 1 Hd
Embeddings1
MTEBMean task scoreyesterday#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedyesterday#539 tok/sbest of the pickedGLM 5.3 Flash#1522 tok/sGPT-6.1 Sol#1323 tok/sDeepSeek V4 Pro 0813
Price1
AA PriceBlended priceyesterday#7$2.15GLM-5.3#6$2.00GPT-6.1 Terra#3$0.53best of the pickedDeepSeek V4.1 Flash
Usage1
OpenRouterWeekly tokensyesterday#213.2T tokGLM 5.3 Flash#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