StepFun vs Microsoft vs DeepSeek vs ElevenLabs

Head to head on 11 boards: DeepSeek places best on 8, Microsoft places best on 2, ElevenLabs places best on 1 and StepFun places best on 0. All 4 ranked on 0 of 21 boards.

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

StepFunMicrosoftDeepSeekElevenLabs

Board	Read	StepFun	Microsoft	DeepSeek	ElevenLabs
Chat2
Text ArenaArena ratingtodaytoday	Nov 9todaytoday	#701,448Step 5 Preview		#321,475best of the pickedDeepSeek V4.1 Flash
MultiChallengeScoretodaytoday	Nov 9todaytoday			#574.9%DeepSeek V4P1 Flash
Reasoning6
AA IntelligenceIndextodaytoday	Nov 9todaytoday	#2328.5Step 5 Preview		#1632.6best of the pickedDeepSeek V4.1 Flash
MMLU-ProAccuracy · staletodaytoday	Nov 9todaytoday		#7576.0%Phi 4 Plus	#3385.0%best of the pickedDeepSeek-V3.2
LiveBenchGlobal averagetodaytoday	Nov 9todaytoday			#881.1%DeepSeek V4.1 Flash
Epoch ECIECItodaytoday	Nov 9todaytoday			#19159.3DeepSeek V4.1 Flash
ARC-AGI-2Scoretodaytoday	Nov 9todaytoday			#1978.1%DeepSeek V4.1 Flash
GPQA DiamondAccuracytodaytoday	Nov 9todaytoday			#2193.2%DeepSeek V4.1 Flash
Coding3
WebDev ArenaArena ratingtodaytoday	Nov 9todaytoday	#381,572Step 5 Preview		#141,665best of the pickedDeepSeek V4.1 Flash
Aider PolyglotPass rate · staletodaytoday	Nov 9todaytoday			#874.2%DeepSeek-V3.2
SWE-bench VerifiedResolved · staletodaytoday	Nov 9todaytoday			#1170.0%DeepSeek-V3.2
Agents and tools1
BFCLOverall accuracy · staletodaytoday	Nov 9todaytoday		#5028.8%Phi 4	#1256.7%best of the pickedDeepSeek-V3.2
Vision1
Vision ArenaArena ratingtodaytoday	Nov 9todaytoday	#511,247Step 5 Preview		#341,263best of the pickedDeepSeek V4.1 Flash
Image2
Image EditArena ratingtodaytoday	Nov 9todaytoday	#51996Step1x Edit	#41,467best of the pickedMAI Image 2.7
Text-to-ImageArena ratingtodaytoday	Nov 9todaytoday		#61,330MAI Image 2.6
Speech2
Speech ArenaArena ratingtodaytoday	Nov 9todaytoday	#181,216Stepaudio 2.5 TTS	#311,145Azure Hd 2.5		#11,339best of the pickedEleven V4
Open ASRAverage WERtodaytoday	Nov 9todaytoday		#35.55 WERbest of the pickedazure-speech-09-2026 (microsoft)		#55.93 WERscribe v2 (elevenlabs)
Embeddings1
MTEBMean task scoretodaytoday	Nov 9todaytoday		#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedtodaytoday	Nov 9todaytoday	#2214 tok/sStep 5 Preview		#1323 tok/sbest of the pickedDeepSeek V4 Pro 0813
Price1
AA PriceBlended pricetodaytoday	Nov 9todaytoday			#3$0.53DeepSeek V4.1 Flash
Usage1
OpenRouterWeekly tokenstodaytoday	Nov 9todaytoday	#57.2T tokStep 5 Preview		#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.