Kokoro vs Google vs Meta vs Microsoft

Head to head on 25 boards: Google places best on 13, Meta places best on 8, Microsoft places best on 4 and Kokoro places best on 0. All 4 ranked on 1 of 28 boards.

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

KKokoroGoogleMetaMicrosoft

Board	Read	KKokoro	Google	Meta	Microsoft
Chat2
MultiChallengeScoretodaytoday	Sep 27todaytoday		#371.4%Gemini 3.1 Pro Preview	#175.5%best of the pickedMuse Spark
Text ArenaArena ratingtodaytoday	Sep 27todaytoday		#81,492Gemini 3.8 Flash	#61,496best of the pickedMuse Spark 1.2
Reasoning7
MMLU-ProAccuracy · staletodaytoday	Sep 27todaytoday		#191.2%best of the pickedGemini 3.1 Pro Preview	#4782.8%Llama4 Behemoth	#7576.0%Phi 4 Plus
GPQA DiamondAccuracytodaytoday	Sep 27todaytoday		#295.4%best of the pickedGemini 3.8 Flash	#3589.8%Muse Spark
HLEAccuracytodaytoday	Sep 27todaytoday		#346.4%best of the pickedGemini 3.1 Pro Preview	#640.6%Muse Spark
AA IntelligenceIndextodaytoday	Sep 27todaytoday		#1540.9Gemini 3.8 Flash	#448.1best of the pickedMuse Spark 1.3
LiveBenchGlobal averagetodaytoday	Sep 27todaytoday		#1378.8%Gemini 3.7 Flash	#581.6%best of the pickedMuse Spark 1.3
ARC-AGI-2Scoretodaytoday	Sep 27todaytoday		#689.2%best of the pickedGemini 3.8 Flash	#710.0%Llama 4 Maverick Instruct
Epoch ECIECItodaytoday	Sep 27todaytoday		#11157.7best of the pickedGemini 3.7 Flash	#15156.9Muse Spark 1.3
Coding4
SWE-bench VerifiedResolved · staletodaytoday	Sep 27todaytoday		#275.8%best of the pickedGemini 3 Flash	#3621.0%Llama 4 Maverick Instruct
Aider PolyglotPass rate · staletodaytoday	Sep 27todaytoday		#383.1%best of the pickedGemini 2.5 Pro (Jun 2025)	#4315.6%Llama 4 Maverick Instruct
WebDev ArenaArena ratingtodaytoday	Sep 27todaytoday		#201,593Gemini 3.7 Flash	#81,656best of the pickedMuse Spark 1.3
SWE-Bench ProResolvedtodaytoday	Sep 27todaytoday		#958.8%Gemini 3.8 Flash
Agents and tools3
BFCLOverall accuracytodaytoday	Sep 27todaytoday		#372.5%best of the pickedGemini 3 Pro	#3637.3%Llama 4 Maverick 17b 128e	#5028.8%Phi 4
MCP AtlasPass ratetodaytoday	Sep 27todaytoday		#683.6%Gemini 3.5 Flash	#188.1%best of the pickedMuse Spark 1.1
Search ArenaArena ratingtodaytoday	Sep 27todaytoday		#91,210Gemini 3.1 Pro Grounding
Vision2
Vision ArenaArena ratingtodaytoday	Sep 27todaytoday		#101,289Gemini 3 Pro	#51,294best of the pickedMuse Spark 1.3
Document ArenaArena ratingtodaytoday	Sep 27todaytoday		#161,463Gemini 3.5 Flash	#121,471best of the pickedMuse Spark 1.3
Image2
Text-to-ImageArena ratingtodaytoday	Sep 27todaytoday		#91,261Gemini 3.1 Flash Image	#71,276Muse Image	#41,335best of the pickedMAI Image 2.6
Image EditArena ratingtodaytoday	Sep 27todaytoday		#91,390Gemini 3 Pro Image	#61,402Muse Image	#51,429best of the pickedMAI Image 2.6
Video2
Text-to-VideoArena ratingtodaytoday	Sep 27todaytoday		#11,516best of the pickedGemini Omni 1.1 Flash	#91,456Muse Video
Image-to-VideoArena ratingtodaytoday	Sep 27todaytoday		#21,488Gemini Omni 1.1 Flash
Speech2
Speech ArenaArena ratingtodaytoday	Sep 27todaytoday	#481,065Kokoro 82m V1.0	#21,268best of the pickedGemini 3.8 Flash TTS	#89847Metavoice V1	#261,126Azure Hd 2.5
Open ASRAverage WERtodaytoday	Sep 27todaytoday		#669.51 WERgemma-4-E4B-it (google)	#284.84 WERmuse-voice-transcribe (meta)	#23.81 WERbest of the pickedazure-speech-07-2026 (microsoft)
Embeddings1
MTEBMean task scoretodaytoday	Sep 27todaytoday		#568.4%gemini-embedding-001 (google)		#174.3%best of the pickedharrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedtodaytoday	Sep 27todaytoday		#1308 tok/sbest of the pickedGemini 3.8 Flash	#2232 tok/sMuse Spark 1.3
Price1
AA PriceBlended pricetodaytoday	Sep 27todaytoday		#9$1.50best of the pickedGemini 3.8 Flash	#11$2.00Muse Spark 1.3
Usage1
OpenRouterWeekly tokenstodaytoday	Sep 27todaytoday		#142.2T tokbest of the pickedGemini 3.8 Flash	#151.8T tokMuse Spark 1.3 Contributor

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.