Google vs Anthropic vs Microsoft vs MiniMax

Head to head on 28 boards: Anthropic places best on 14, Google places best on 9, Microsoft places best on 4 and MiniMax places best on 1. All 4 ranked on 1 of 28 boards.

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

GoogleAnthropicMicrosoftMiniMax

Board	Read	Google	Anthropic	Microsoft	MiniMax
Chat2
Text ArenaArena ratingtodaytoday	Sep 27todaytoday	#81,492Gemini 3.8 Flash	#11,509best of the pickedClaude Opus 5.5		#761,440MiniMax-M3
MultiChallengeScoretodaytoday	Sep 27todaytoday	#371.4%best of the pickedGemini 3.1 Pro Preview	#1259.0%Claude Opus 4.5
Reasoning7
MMLU-ProAccuracy · staletodaytoday	Sep 27todaytoday	#191.2%best of the pickedGemini 3.1 Pro Preview	#489.1%Claude Opus 4.6	#7576.0%Phi 4 Plus	#688.0%MiniMax M2.1
AA IntelligenceIndextodaytoday	Sep 27todaytoday	#1540.9Gemini 3.8 Flash	#157.6best of the pickedClaude Opus 5.5		#2829.2MiniMax-M3
LiveBenchGlobal averagetodaytoday	Sep 27todaytoday	#1378.8%Gemini 3.7 Flash	#183.4%best of the pickedClaude Fable 5.1		#5567.3%MiniMax-M3
GPQA DiamondAccuracytodaytoday	Sep 27todaytoday	#295.4%best of the pickedGemini 3.8 Flash	#1093.9%Claude Opus 5		#2590.9%MiniMax-M3
Epoch ECIECItodaytoday	Sep 27todaytoday	#11157.7Gemini 3.7 Flash	#2165.0best of the pickedClaude Fable 5.1		#60147.0MiniMax-M3
ARC-AGI-2Scoretodaytoday	Sep 27todaytoday	#689.2%Gemini 3.8 Flash	#293.3%best of the pickedClaude Opus 5.5		#524.9%MiniMax-M2.5
HLEAccuracytodaytoday	Sep 27todaytoday	#346.4%Gemini 3.1 Pro Preview	#246.5%best of the pickedClaude Fable 5.1
Coding4
WebDev ArenaArena ratingtodaytoday	Sep 27todaytoday	#201,593Gemini 3.7 Flash	#11,827best of the pickedClaude Opus 5.5		#461,483MiniMax-M3
SWE-bench VerifiedResolved · staletodaytoday	Sep 27todaytoday	#275.8%Gemini 3 Flash	#176.8%best of the pickedClaude Opus 4.5		#275.8%MiniMax-M2.5
SWE-Bench ProResolvedtodaytoday	Sep 27todaytoday	#958.8%Gemini 3.8 Flash	#198.0%best of the pickedClaude Opus 5
Aider PolyglotPass rate · staletodaytoday	Sep 27todaytoday	#383.1%best of the pickedGemini 2.5 Pro (Jun 2025)	#1072.0%Claude Opus 4
Agents and tools3
BFCLOverall accuracytodaytoday	Sep 27todaytoday	#372.5%Gemini 3 Pro	#177.5%best of the pickedClaude Opus 4.5	#5028.8%Phi 4
MCP AtlasPass ratetodaytoday	Sep 27todaytoday	#683.6%Gemini 3.5 Flash	#287.2%best of the pickedClaude Fable 5.1
Search ArenaArena ratingtodaytoday	Sep 27todaytoday	#91,210Gemini 3.1 Pro Grounding	#21,253best of the pickedClaude Opus 4.6
Vision2
Vision ArenaArena ratingtodaytoday	Sep 27todaytoday	#101,289Gemini 3 Pro	#11,310best of the pickedClaude Fable 5		#471,237MiniMax-M3
Document ArenaArena ratingtodaytoday	Sep 27todaytoday	#161,463Gemini 3.5 Flash	#11,516best of the pickedClaude Opus 5		#271,435MiniMax-M3
Image2
Text-to-ImageArena ratingtodaytoday	Sep 27todaytoday	#91,261Gemini 3.1 Flash Image		#41,335best of the pickedMAI Image 2.6
Image EditArena ratingtodaytoday	Sep 27todaytoday	#91,390Gemini 3 Pro 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			#81,460MiniMax H3
Image-to-VideoArena ratingtodaytoday	Sep 27todaytoday	#21,488Gemini Omni 1.1 Flash			#11,495best of the pickedMiniMax H3
Speech2
Speech ArenaArena ratingtodaytoday	Sep 27todaytoday	#21,268best of the pickedGemini 3.8 Flash TTS		#261,126Azure Hd 2.5	#161,172Speech 2.8 Hd
Open ASRAverage WERtodaytoday	Sep 27todaytoday	#669.51 WERgemma-4-E4B-it (google)		#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	#988 tok/sClaude Opus 5.5
Price1
AA PriceBlended pricetodaytoday	Sep 27todaytoday	#9$1.50best of the pickedGemini 3.8 Flash	#17$4.00Claude Sonnet 5
Usage1
OpenRouterWeekly tokenstodaytoday	Sep 27todaytoday	#142.2T tokbest of the pickedGemini 3.8 Flash	#191.5T tokClaude Sonnet 5

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.