GPT 4o vs Gemini 4 Argon vs Claude Fable 5.1 vs DeepSeek V4P1 Flash

One row per board where at least one is ranked, from each board's current capture.

GPT 4o
Gemini 4 Argon
Claude Fable 5.1
DeepSeek V4P1 Flash

Head to head on 13 boards: Gemini 4 Argon places best on 7, Claude Fable 5.1 places best on 6, GPT 4o places best on 0 and DeepSeek V4P1 Flash places best on 0. All 4 ranked on 0 of 19 boards.

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

Board	Read	GPT 4o	Gemini 4 Argon	Claude Fable 5.1	DeepSeek V4P1 Flash
Chat2
Text ArenaArena ratingyesterday	Nov 9yesterday	#771,443	#21,523best of the picked	#61,504
MultiChallengeScoreyesterday	Nov 9yesterday		#278.7%best of the picked		#574.9%
Reasoning7
ARC-AGI-2Scoreyesterday	Nov 9yesterday	#840.0%	#591.3%best of the picked	#790.0%
HLEAccuracyyesterday	Nov 9yesterday	#442.7%		#246.5%best of the picked
Epoch ECIECIyesterday	Nov 9yesterday		#6166.4	#5166.9best of the picked
AA IntelligenceIndexyesterday	Nov 9yesterday		#750.4best of the picked	#950.0
GPQA DiamondAccuracyyesterday	Nov 9yesterday		#196.4%
LiveBenchGlobal averageyesterday	Nov 9yesterday			#183.4%
MMLU-ProAccuracy · staleyesterday	Nov 9yesterday	#7277.9%
Coding4
SWE-Bench ProResolvedyesterday	Nov 9yesterday		#392.2%	#292.2%best of the picked
WebDev ArenaArena ratingyesterday	Nov 9yesterday		#101,683	#51,746best of the picked
Aider PolyglotPass rate · staleyesterday	Nov 9yesterday	#2845.3%
SWE-bench VerifiedResolved · staleyesterday	Nov 9yesterday	#3521.6%
Agents and tools2
MCP AtlasPass rateyesterday	Nov 9yesterday		#190.7%best of the picked	#387.2%
Search ArenaArena ratingyesterday	Nov 9yesterday	#391,084		#71,227best of the picked
Vision2
Vision ArenaArena ratingyesterday	Nov 9yesterday	#561,239		#131,288best of the picked
Document ArenaArena ratingyesterday	Nov 9yesterday			#21,499
Speed1
AA SpeedOutput speedyesterday	Nov 9yesterday		#1028 tok/sbest of the picked	#1422 tok/s
Price1
AA PriceBlended priceyesterday	Nov 9yesterday		#13$8.00best of the picked	#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.

More comparisons