Institute Of Foundation Models vs Meta vs Microsoft vs Xiaomi

Head to head on 13 boards: Meta places best on 7, Microsoft places best on 4, Xiaomi places best on 2 and Institute Of Foundation Models places best on 0. All 4 ranked on 0 of 25 boards.

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

IOInstitute Of Foundation ModelsMetaMicrosoftXiaomi

Board	Read	IOInstitute Of Foundation Models	Meta	Microsoft	Xiaomi
Chat2
Text ArenaArena ratingtodaytoday	Oct 6todaytoday		#81,494best of the pickedMuse Spark 1.3		#231,480MiMo-V2.6-Pro
MultiChallengeScoretodaytoday	Oct 6todaytoday		#175.5%Muse Spark
Reasoning7
AA IntelligenceIndextodaytoday	Oct 6todaytoday	#2830.5K2 Horizon 375B A23B	#748.1best of the pickedMuse Spark 1.3		#946.3MiMo-V2.6-Pro
MMLU-ProAccuracy · staletodaytoday	Oct 6todaytoday		#4782.8%best of the pickedLlama4 Behemoth	#7576.0%Phi 4 Plus
HLEAccuracytodaytoday	Oct 6todaytoday		#640.6%Muse Spark
LiveBenchGlobal averagetodaytoday	Oct 6todaytoday		#681.6%Muse Spark 1.3
Epoch ECIECItodaytoday	Oct 6todaytoday		#19156.8Muse Spark 1.3
GPQA DiamondAccuracytodaytoday	Oct 6todaytoday		#4189.8%Muse Spark
ARC-AGI-2Scoretodaytoday	Oct 6todaytoday		#750.0%Llama 4 Maverick Instruct
Coding3
WebDev ArenaArena ratingtodaytoday	Oct 6todaytoday		#111,657best of the pickedMuse Spark 1.3		#201,618MiMo-V2.6-Pro
SWE-bench VerifiedResolved · staletodaytoday	Oct 6todaytoday		#3621.0%Llama 4 Maverick Instruct
Aider PolyglotPass rate · staletodaytoday	Oct 6todaytoday		#4315.6%Llama 4 Maverick Instruct
Agents and tools2
BFCLOverall accuracytodaytoday	Oct 6todaytoday		#3637.3%best of the pickedLlama 4 Maverick 17b 128e	#5028.8%Phi 4
MCP AtlasPass ratetodaytoday	Oct 6todaytoday		#188.1%Muse Spark 1.1
Vision2
Vision ArenaArena ratingtodaytoday	Oct 6todaytoday		#61,294best of the pickedMuse Spark		#461,247MiMo-V2.6-Flash
Document ArenaArena ratingtodaytoday	Oct 6todaytoday		#121,471Muse Spark 1.3
Image2
Text-to-ImageArena ratingtodaytoday	Oct 6todaytoday		#71,274Muse Image	#51,333best of the pickedMAI Image 2.6
Image EditArena ratingtodaytoday	Oct 6todaytoday		#61,403Muse Image	#51,427best of the pickedMAI Image 2.6
Video1
Text-to-VideoArena ratingtodaytoday	Oct 6todaytoday		#91,456Muse Video
Speech2
Speech ArenaArena ratingtodaytoday	Oct 6todaytoday		#92850Metavoice V1	#281,131best of the pickedAzure Hd 2.5	#591,055MiMo V2.5 TTS
Open ASRAverage WERtodaytoday	Oct 6todaytoday		#294.84 WERmuse-voice-transcribe (meta)	#23.81 WERbest of the pickedazure-speech-07-2026 (microsoft)
Embeddings1
MTEBMean task scoretodaytoday	Oct 6todaytoday			#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedtodaytoday	Oct 6todaytoday	#7124 tok/sK2 Horizon 375B A23B	#4152 tok/sbest of the pickedMuse Spark 1.3		#2051 tok/sMiMo-V2.6-Flash
Price1
AA PriceBlended pricetodaytoday	Oct 6todaytoday		#12$2.00Muse Spark 1.3		#1$0.17best of the pickedMiMo-V2.6-Flash
Usage1
OpenRouterWeekly tokenstodaytoday	Oct 6todaytoday		#161.4T tokMuse Spark 1.3 Contributor		#49.7T tokbest of the pickedMiMo-V2.6-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.