Edge0 vs Anthropic vs DeepSeek vs Microsoft

Head to head on 16 boards: Anthropic places best on 13, DeepSeek places best on 2, Microsoft places best on 1 and Edge0 places best on 0. All 4 ranked on 0 of 26 boards.

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

EEdge0AnthropicDeepSeekMicrosoft

Board	Read	EEdge0	Anthropic	DeepSeek	Microsoft
Chat2
Text ArenaArena ratingtodaytoday	Oct 8todaytoday		#21,505best of the pickedClaude Opus 4.6	#321,474DeepSeek V4.1 Flash
MultiChallengeScoretodaytoday	Oct 8todaytoday		#1359.0%best of the pickedClaude Opus 4.5	#2546.1%DeepSeek V3P1
Reasoning7
MMLU-ProAccuracy · staletodaytoday	Oct 8todaytoday		#489.1%best of the pickedClaude Opus 4.6	#3385.0%DeepSeek-V3.2	#7576.0%Phi 4 Plus
AA IntelligenceIndextodaytoday	Oct 8todaytoday		#157.6best of the pickedClaude Opus 5.5	#2139.5DeepSeek V4.1 Flash
Epoch ECIECItodaytoday	Oct 8todaytoday		#1167.3best of the pickedClaude Opus 5.5	#29155.3DeepSeek V4 Pro 0813
LiveBenchGlobal averagetodaytoday	Oct 8todaytoday		#183.4%best of the pickedClaude Fable 5.1	#781.1%DeepSeek V4.1 Flash
GPQA DiamondAccuracytodaytoday	Oct 8todaytoday		#295.6%best of the pickedClaude Sonnet 5.5	#2491.7%DeepSeek V4 Pro 0813
ARC-AGI-2Scoretodaytoday	Oct 8todaytoday		#393.3%best of the pickedClaude Opus 5.5	#2072.9%DeepSeek V4.1 Flash
HLEAccuracytodaytoday	Oct 8todaytoday		#246.5%Claude Fable 5.1
Coding4
WebDev ArenaArena ratingtodaytoday	Oct 8todaytoday		#11,814best of the pickedClaude Opus 5.5	#191,619DeepSeek V4.1 Flash
SWE-bench VerifiedResolved · staletodaytoday	Oct 8todaytoday		#176.8%best of the pickedClaude Opus 4.5	#1170.0%DeepSeek-V3.2
Aider PolyglotPass rate · staletodaytoday	Oct 8todaytoday		#1072.0%Claude Opus 4	#874.2%best of the pickedDeepSeek-V3.2
SWE-Bench ProResolvedtodaytoday	Oct 8todaytoday		#198.0%Claude Opus 5
Agents and tools3
BFCLOverall accuracytodaytoday	Oct 8todaytoday		#177.5%best of the pickedClaude Opus 4.5	#1256.7%DeepSeek-V3.2	#5028.8%Phi 4
MCP AtlasPass ratetodaytoday	Oct 8todaytoday		#287.2%Claude Fable 5.1
Search ArenaArena ratingtodaytoday	Oct 8todaytoday		#21,253Claude Opus 4.6
Vision2
Vision ArenaArena ratingtodaytoday	Oct 8todaytoday		#11,309Claude Fable 5
Document ArenaArena ratingtodaytoday	Oct 8todaytoday		#11,516Claude Opus 5
Image2
Text-to-ImageArena ratingtodaytoday	Oct 8todaytoday				#51,332MAI Image 2.6
Image EditArena ratingtodaytoday	Oct 8todaytoday				#51,428MAI Image 2.6
Speech2
Open ASRAverage WERtodaytoday	Oct 8todaytoday	#174.47 WERARK-ASR-3B (Edge0)			#23.81 WERbest of the pickedazure-speech-07-2026 (microsoft)
Speech ArenaArena ratingtodaytoday	Oct 8todaytoday				#281,131Azure Hd 2.5
Embeddings1
MTEBMean task scoretodaytoday	Oct 8todaytoday				#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedtodaytoday	Oct 8todaytoday		#2243 tok/sbest of the pickedClaude Haiku 5.5	#3223 tok/sDeepSeek V4.1 Flash
Price1
AA PriceBlended pricetodaytoday	Oct 8todaytoday		#2$0.20best of the pickedClaude Haiku 5.5	#7$0.53DeepSeek V4.1 Flash
Usage1
OpenRouterWeekly tokenstodaytoday	Oct 8todaytoday		#93.4T tokClaude Opus 5.5	#133.6T 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.