Claude Sonnet 4 vs Qwen3.8 Max (0902) vs GPT-6 Astra vs Gemini 4 Argon

Head to head on 14 boards: GPT-6 Astra places best on 7, Gemini 4 Argon places best on 4, Qwen3.8 Max (0902) places best on 3 and Claude Sonnet 4 places best on 0. All 4 ranked on 1 of 19 boards.

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

Claude Sonnet 4Qwen3.8 Max (0902)GPT-6 AstraGemini 4 Argon

Board	Read	Claude Sonnet 4	Qwen3.8 Max (0902)	GPT-6 Astra	Gemini 4 Argon
Chat2
Text ArenaArena rating1dyesterday	Nov 91dyesterday		#201,483	#311,475	#21,523best of the picked
MultiChallengeScore1dyesterday	Nov 91dyesterday	#2157.1%			#278.7%best of the picked
Reasoning7
GPQA DiamondAccuracy1dyesterday	Nov 91dyesterday	#9479.2%	#2692.7%	#295.8%	#196.4%best of the picked
Epoch ECIECI1dyesterday	Nov 91dyesterday		#27157.4	#1169.1best of the picked	#6166.4
ARC-AGI-2Score1dyesterday	Nov 91dyesterday	#625.9%		#195.0%best of the picked	#591.3%
AA IntelligenceIndex1dyesterday	Nov 91dyesterday		#1533.7	#356.9best of the picked	#750.4
HLEAccuracy1dyesterday	Nov 91dyesterday	#337.8%		#154.8%best of the picked
LiveBenchGlobal average1dyesterday	Nov 91dyesterday		#1678.5%	#482.2%best of the picked
MMLU-ProAccuracy · stale1dyesterday	Nov 91dyesterday	#4183.7%
Coding4
WebDev ArenaArena rating1dyesterday	Nov 91dyesterday		#121,677	#31,770best of the picked	#101,683
SWE-Bench ProResolved1dyesterday	Nov 91dyesterday			#490.2%	#392.2%best of the picked
Aider PolyglotPass rate · stale1dyesterday	Nov 91dyesterday	#1661.3%
SWE-bench VerifiedResolved · stale1dyesterday	Nov 91dyesterday	#1764.9%
Agents and tools2
Search ArenaArena rating1dyesterday	Nov 91dyesterday		#61,228	#31,245best of the picked
MCP AtlasPass rate1dyesterday	Nov 91dyesterday				#190.7%
Vision2
Vision ArenaArena rating1dyesterday	Nov 91dyesterday	#761,206	#21,300best of the picked	#171,285
Document ArenaArena rating1dyesterday	Nov 91dyesterday			#111,477
Speed1
AA SpeedOutput speed1dyesterday	Nov 91dyesterday		#260 tok/sbest of the picked	#1621 tok/s	#1028 tok/s
Price1
AA PriceBlended price1dyesterday	Nov 91dyesterday		#8$3.00best of the picked	#17$20.0	#13$8.00

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.