o3 vs Claude Fable 5.1 vs Muse Spark 1.1 vs DeepSeek V4P1 Flash

Head to head on 11 boards: Claude Fable 5.1 places best on 9, Muse Spark 1.1 places best on 2, o3 places best on 0 and DeepSeek V4P1 Flash places best on 0. All 4 ranked on 0 of 20 boards.

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

o3Claude Fable 5.1Muse Spark 1.1DeepSeek V4P1 Flash

Board	Read	o3	Claude Fable 5.1	Muse Spark 1.1	DeepSeek V4P1 Flash
Chat2
MultiChallengeScoretodaytoday	Nov 9todaytoday	#2256.6%		#475.3%best of the picked	#574.9%
Text ArenaArena ratingtodaytoday	Nov 9todaytoday		#61,504best of the picked	#131,490
Reasoning7
Epoch ECIECItodaytoday	Nov 9todaytoday	#77147.0	#5166.9best of the picked	#42154.9
LiveBenchGlobal averagetodaytoday	Nov 9todaytoday		#183.4%best of the picked	#3575.3%
HLEAccuracytodaytoday	Nov 9todaytoday	#2020.3%	#246.5%best of the picked
ARC-AGI-2Scoretodaytoday	Nov 9todaytoday	#606.5%	#790.0%best of the picked
AA IntelligenceIndextodaytoday	Nov 9todaytoday		#950.0
MMLU-ProAccuracy · staletodaytoday	Nov 9todaytoday	#3385.0%
GPQA DiamondAccuracytodaytoday	Nov 9todaytoday	#8981.8%
Coding4
WebDev ArenaArena ratingtodaytoday	Nov 9todaytoday		#51,746best of the picked	#441,542
SWE-Bench ProResolvedtodaytoday	Nov 9todaytoday		#292.2%
Aider PolyglotPass rate · staletodaytoday	Nov 9todaytoday	#481.3%
SWE-bench VerifiedResolved · staletodaytoday	Nov 9todaytoday	#2158.4%
Agents and tools3
MCP AtlasPass ratetodaytoday	Nov 9todaytoday		#387.2%	#288.1%best of the picked
Search ArenaArena ratingtodaytoday	Nov 9todaytoday	#201,197	#71,227best of the picked
BFCLOverall accuracy · staletodaytoday	Nov 9todaytoday	#763.0%
Vision2
Vision ArenaArena ratingtodaytoday	Nov 9todaytoday	#701,216	#131,288best of the picked	#241,279
Document ArenaArena ratingtodaytoday	Nov 9todaytoday		#21,499best of the picked	#91,479
Speed1
AA SpeedOutput speedtodaytoday	Nov 9todaytoday		#1422 tok/s
Price1
AA PriceBlended pricetodaytoday	Nov 9todaytoday		#17$20.0

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.