Grok 4 vs Claude Fable 5.1 vs GPT-6 Astra vs Gemini 4 Argon

Head to head on 15 boards: GPT-6 Astra places best on 6, Gemini 4 Argon places best on 5, Claude Fable 5.1 places best on 4 and Grok 4 places best on 0. All 4 ranked on 2 of 19 boards.

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

Grok 4Claude Fable 5.1GPT-6 AstraGemini 4 Argon

Board	Read	Grok 4	Claude Fable 5.1	GPT-6 Astra	Gemini 4 Argon
Chat2
Text ArenaArena ratingtodaytoday	Nov 9todaytoday		#61,504	#311,475	#21,523best of the picked
MultiChallengeScoretodaytoday	Nov 9todaytoday				#278.7%
Reasoning7
Epoch ECIECItodaytoday	Nov 9todaytoday	#78146.9	#5166.9	#1169.1best of the picked	#6166.4
ARC-AGI-2Scoretodaytoday	Nov 9todaytoday	#5416.0%	#790.0%	#195.0%best of the picked	#591.3%
GPQA DiamondAccuracytodaytoday	Nov 9todaytoday	#6887.0%		#295.8%	#196.4%best of the picked
AA IntelligenceIndextodaytoday	Nov 9todaytoday		#950.0	#356.9best of the picked	#750.4
HLEAccuracytodaytoday	Nov 9todaytoday		#246.5%	#154.8%best of the picked
LiveBenchGlobal averagetodaytoday	Nov 9todaytoday		#183.4%best of the picked	#482.2%
MMLU-ProAccuracy · staletodaytoday	Nov 9todaytoday	#1887.0%
Coding3
SWE-Bench ProResolvedtodaytoday	Nov 9todaytoday		#292.2%best of the picked	#490.2%	#392.2%
WebDev ArenaArena ratingtodaytoday	Nov 9todaytoday		#51,746	#31,770best of the picked	#101,683
Aider PolyglotPass rate · staletodaytoday	Nov 9todaytoday	#579.6%
Agents and tools3
Search ArenaArena ratingtodaytoday	Nov 9todaytoday	#381,123	#71,227	#31,245best of the picked
MCP AtlasPass ratetodaytoday	Nov 9todaytoday		#387.2%		#190.7%best of the picked
BFCLOverall accuracy · staletodaytoday	Nov 9todaytoday	#863.0%
Vision2
Document ArenaArena ratingtodaytoday	Nov 9todaytoday		#21,499best of the picked	#111,477
Vision ArenaArena ratingtodaytoday	Nov 9todaytoday		#131,288best of the picked	#171,285
Speed1
AA SpeedOutput speedtodaytoday	Nov 9todaytoday		#1422 tok/s	#1621 tok/s	#1028 tok/sbest of the picked
Price1
AA PriceBlended pricetodaytoday	Nov 9todaytoday		#17$20.0	#17$20.0	#13$8.00best of the picked

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.