StepFun vs Anthropic

Each lab shows its best-ranked model on every board. One row per board where at least one is ranked, from each board's current capture.

StepFun
Anthropic

Add:

Head to head on 6 boards: Anthropic places best on 5 and StepFun places best on 1. Both ranked on 6 of 23 boards.

Board	Read	StepFun	Anthropic
Chat2
Text ArenaArena ratingtoday	Nov 9today	#701,448Step 5 Preview	#41,505best of the pickedClaude Opus 5.5
MultiChallengeScoretoday	Nov 9today		#1067.7%Claude Haiku 5.5
Reasoning7
AA IntelligenceIndextoday	Nov 9today	#2328.5Step 5 Preview	#259.1best of the pickedClaude Opus 5.5
LiveBenchGlobal averagetoday	Nov 9today		#183.4%Claude Fable 5.1
HLEAccuracytoday	Nov 9today		#246.5%Claude Fable 5.1
GPQA DiamondAccuracytoday	Nov 9today		#395.6%Claude Sonnet 5.5
Epoch ECIECItoday	Nov 9today		#3168.4Claude Opus 5.5
ARC-AGI-2Scoretoday	Nov 9today		#393.3%Claude Opus 5.5
MMLU-ProAccuracy · staletoday	Nov 9today		#489.1%Claude Opus 4.6
Coding4
WebDev ArenaArena ratingtoday	Nov 9today	#381,572Step 5 Preview	#11,814best of the pickedClaude Opus 5.5
SWE-Bench ProResolvedtoday	Nov 9today		#198.0%Claude Opus 5
SWE-bench VerifiedResolved · staletoday	Nov 9today		#176.8%Claude Opus 4.5
Aider PolyglotPass rate · staletoday	Nov 9today		#1072.0%Claude Opus 4
Agents and tools3
BFCLOverall accuracy · staletoday	Nov 9today		#177.5%Claude Opus 4.5
MCP AtlasPass ratetoday	Nov 9today		#387.2%Claude Fable 5.1
Search ArenaArena ratingtoday	Nov 9today		#51,229Claude Fable 5
Vision2
Vision ArenaArena ratingtoday	Nov 9today	#511,247Step 5 Preview	#11,309best of the pickedClaude Fable 5
Document ArenaArena ratingtoday	Nov 9today		#11,499Claude Fable 5
Image1
Image EditArena ratingtoday	Nov 9today	#51996Step1x Edit
Speech1
Speech ArenaArena ratingtoday	Nov 9today	#181,216Stepaudio 2.5 TTS
Speed1
AA SpeedOutput speedtoday	Nov 9today	#2214 tok/sStep 5 Preview	#931 tok/sbest of the pickedClaude Sonnet 5.5
Price1
AA PriceBlended pricetoday	Nov 9today		#1$0.20Claude Haiku 5.5
Usage1
OpenRouterWeekly tokenstoday	Nov 9today	#57.2T tokbest of the pickedStep 5 Preview	#66.8T tokClaude Opus 5.5

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.

More comparisons