Llama 4 Maverick Instruct vs Qwen3.8 Max (0902) vs Gemini 4 Argon vs GPT-6 Astra

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

Llama 4 Maverick Instruct
Qwen3.8 Max (0902)
Gemini 4 Argon
GPT-6 Astra

Head to head on 13 boards: GPT-6 Astra places best on 7, Qwen3.8 Max (0902) places best on 3, Gemini 4 Argon places best on 3 and Llama 4 Maverick Instruct 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.

Board	Read	Llama 4 Maverick Instruct	Qwen3.8 Max (0902)	Gemini 4 Argon	GPT-6 Astra
Chat2
Text ArenaArena ratingyesterday	Nov 9yesterday		#201,483	#21,523best of the picked	#311,475
MultiChallengeScoreyesterday	Nov 9yesterday			#278.7%
Reasoning6
GPQA DiamondAccuracyyesterday	Nov 9yesterday		#2692.7%	#196.4%best of the picked	#295.8%
Epoch ECIECIyesterday	Nov 9yesterday		#27157.4	#6166.4	#1169.1best of the picked
ARC-AGI-2Scoreyesterday	Nov 9yesterday	#840.0%		#591.3%	#195.0%best of the picked
AA IntelligenceIndexyesterday	Nov 9yesterday		#1533.7	#750.4	#356.9best of the picked
HLEAccuracyyesterday	Nov 9yesterday	#365.7%			#154.8%best of the picked
LiveBenchGlobal averageyesterday	Nov 9yesterday		#1678.5%		#482.2%best of the picked
Coding4
WebDev ArenaArena ratingyesterday	Nov 9yesterday		#121,677	#101,683	#31,770best of the picked
SWE-Bench ProResolvedyesterday	Nov 9yesterday			#392.2%best of the picked	#490.2%
SWE-bench VerifiedResolved · staleyesterday	Nov 9yesterday	#3621.0%
Aider PolyglotPass rate · staleyesterday	Nov 9yesterday	#4315.6%
Agents and tools2
Search ArenaArena ratingyesterday	Nov 9yesterday		#61,228		#31,245best of the picked
MCP AtlasPass rateyesterday	Nov 9yesterday			#190.7%
Vision2
Vision ArenaArena ratingyesterday	Nov 9yesterday		#21,300best of the picked		#171,285
Document ArenaArena ratingyesterday	Nov 9yesterday				#111,477
Speed1
AA SpeedOutput speedyesterday	Nov 9yesterday		#260 tok/sbest of the picked	#1028 tok/s	#1621 tok/s
Price1
AA PriceBlended priceyesterday	Nov 9yesterday		#8$3.00best of the picked	#13$8.00	#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