Bagel vs GPT-6 Astra vs Claude Fable 5.1 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 Bagel places best on 0. All 4 ranked on 0 of 18 boards.

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

BagelGPT-6 AstraClaude Fable 5.1Gemini 4 Argon

Board	Read	Bagel	GPT-6 Astra	Claude Fable 5.1	Gemini 4 Argon
Chat2
Text ArenaArena ratingtodaytoday	Nov 9todaytoday		#311,475	#61,504	#21,523best of the picked
MultiChallengeScoretodaytoday	Nov 9todaytoday				#278.7%
Reasoning6
Epoch ECIECItodaytoday	Nov 9todaytoday		#1169.1best of the picked	#5166.9	#6166.4
ARC-AGI-2Scoretodaytoday	Nov 9todaytoday		#195.0%best of the picked	#790.0%	#591.3%
AA IntelligenceIndextodaytoday	Nov 9todaytoday		#356.9best of the picked	#950.0	#750.4
HLEAccuracytodaytoday	Nov 9todaytoday		#154.8%best of the picked	#246.5%
GPQA DiamondAccuracytodaytoday	Nov 9todaytoday		#295.8%		#196.4%best of the picked
LiveBenchGlobal averagetodaytoday	Nov 9todaytoday		#482.2%	#183.4%best of the picked
Coding2
SWE-Bench ProResolvedtodaytoday	Nov 9todaytoday		#490.2%	#292.2%best of the picked	#392.2%
WebDev ArenaArena ratingtodaytoday	Nov 9todaytoday		#31,770best of the picked	#51,746	#101,683
Agents and tools2
MCP AtlasPass ratetodaytoday	Nov 9todaytoday			#387.2%	#190.7%best of the picked
Search ArenaArena ratingtodaytoday	Nov 9todaytoday		#31,245best of the picked	#71,227
Vision2
Document ArenaArena ratingtodaytoday	Nov 9todaytoday		#111,477	#21,499best of the picked
Vision ArenaArena ratingtodaytoday	Nov 9todaytoday		#171,285	#131,288best of the picked
Image2
Image EditArena ratingtodaytoday	Nov 9todaytoday	#501,026
Text-to-ImageArena ratingtodaytoday	Nov 9todaytoday	#71897
Speed1
AA SpeedOutput speedtodaytoday	Nov 9todaytoday		#1621 tok/s	#1422 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.