Zyphra vs Anthropic vs DeepSeek

• ZZyphra
• Anthropic
• DeepSeek

Add a lab

Add:OpenAIGoogleMetaMicrosoft

Head to head on 15 boards: Anthropic places best on 11, DeepSeek places best on 4 and Zyphra places best on 0. All 3 ranked on 0 of 22 boards.

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

ZZyphraAnthropicDeepSeek

Board	Read	ZZyphra	Anthropic	DeepSeek
Chat2
Text ArenaArena ratingtodaytoday	Sep 27todaytoday		#11,509best of the pickedClaude Opus 5.5	#251,477DeepSeek V4.1 Flash
MultiChallengeScoretodaytoday	Sep 27todaytoday		#1259.0%best of the pickedClaude Opus 4.5	#2446.1%DeepSeek V3P1
Reasoning7
AA IntelligenceIndextodaytoday	Sep 27todaytoday		#157.6best of the pickedClaude Opus 5.5	#1839.5DeepSeek V4.1 Flash
LiveBenchGlobal averagetodaytoday	Sep 27todaytoday		#183.4%best of the pickedClaude Fable 5.1	#681.1%DeepSeek V4.1 Flash
Epoch ECIECItodaytoday	Sep 27todaytoday		#2165.0best of the pickedClaude Fable 5.1	#24155.4DeepSeek V4 Pro 0813
ARC-AGI-2Scoretodaytoday	Sep 27todaytoday		#293.3%best of the pickedClaude Opus 5.5	#2361.4%DeepSeek V4 Flash Vision
MMLU-ProAccuracy · staletodaytoday	Sep 27todaytoday		#489.1%best of the pickedClaude Opus 4.6	#3385.0%DeepSeek-V3.2
GPQA DiamondAccuracytodaytoday	Sep 27todaytoday		#1093.9%best of the pickedClaude Opus 5	#2091.7%DeepSeek V4 Pro 0813
HLEAccuracytodaytoday	Sep 27todaytoday		#246.5%Claude Fable 5.1
Coding4
WebDev ArenaArena ratingtodaytoday	Sep 27todaytoday		#11,827best of the pickedClaude Opus 5.5	#131,621DeepSeek V4.1 Flash
SWE-bench VerifiedResolved · staletodaytoday	Sep 27todaytoday		#176.8%best of the pickedClaude Opus 4.5	#1170.0%DeepSeek-V3.2
Aider PolyglotPass rate · staletodaytoday	Sep 27todaytoday		#1072.0%Claude Opus 4	#874.2%best of the pickedDeepSeek-V3.2
SWE-Bench ProResolvedtodaytoday	Sep 27todaytoday		#198.0%Claude Opus 5
Agents and tools3
BFCLOverall accuracytodaytoday	Sep 27todaytoday		#177.5%best of the pickedClaude Opus 4.5	#1256.7%DeepSeek-V3.2
MCP AtlasPass ratetodaytoday	Sep 27todaytoday		#287.2%Claude Fable 5.1
Search ArenaArena ratingtodaytoday	Sep 27todaytoday		#21,253Claude Opus 4.6
Vision2
Vision ArenaArena ratingtodaytoday	Sep 27todaytoday		#11,310Claude Fable 5
Document ArenaArena ratingtodaytoday	Sep 27todaytoday		#11,516Claude Opus 5
Speech1
Speech ArenaArena ratingtodaytoday	Sep 27todaytoday	#741,000Zonos V0.1
Speed1
AA SpeedOutput speedtodaytoday	Sep 27todaytoday		#988 tok/sClaude Opus 5.5	#3232 tok/sbest of the pickedDeepSeek V4.1 Flash
Price1
AA PriceBlended pricetodaytoday	Sep 27todaytoday		#17$4.00Claude Sonnet 5	#4$0.53best of the pickedDeepSeek V4.1 Flash
Usage1
OpenRouterWeekly tokenstodaytoday	Sep 27todaytoday		#191.5T tokClaude Sonnet 5	#118.6T 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.