Gemini 3 Pro vs Qwen3.8 Max (0902) vs Inkling Small 2 vs GPT-6 Astra

Head to head on 15 boards: GPT-6 Astra places best on 10, Qwen3.8 Max (0902) places best on 3, Gemini 3 Pro places best on 1 and Inkling Small 2 places best on 1. All 4 ranked on 0 of 19 boards.

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

Gemini 3 ProQwen3.8 Max (0902)?Inkling Small 2GPT-6 Astra

Board	Read	Gemini 3 Pro	Qwen3.8 Max (0902)	?Inkling Small 2	GPT-6 Astra
Chat2
Text ArenaArena ratingtodaytoday	Nov 9todaytoday	#181,486best of the picked	#201,483		#311,475
MultiChallengeScoretodaytoday	Nov 9todaytoday	#1165.7%
Reasoning7
Epoch ECIECItodaytoday	Nov 9todaytoday	#50152.9	#27157.4		#1169.1best of the picked
GPQA DiamondAccuracytodaytoday	Nov 9todaytoday	#2792.6%	#2692.7%		#295.8%best of the picked
HLEAccuracytodaytoday	Nov 9todaytoday	#837.5%			#154.8%best of the picked
ARC-AGI-2Scoretodaytoday	Nov 9todaytoday	#4831.1%			#195.0%best of the picked
AA IntelligenceIndextodaytoday	Nov 9todaytoday		#1533.7		#356.9best of the picked
LiveBenchGlobal averagetodaytoday	Nov 9todaytoday		#1678.5%		#482.2%best of the picked
MMLU-ProAccuracy · staletodaytoday	Nov 9todaytoday	#290.1%
Coding3
WebDev ArenaArena ratingtodaytoday	Nov 9todaytoday	#681,440	#121,677		#31,770best of the picked
SWE-Bench ProResolvedtodaytoday	Nov 9todaytoday			#986.3%	#490.2%best of the picked
SWE-bench VerifiedResolved · staletodaytoday	Nov 9todaytoday	#574.2%
Agents and tools3
Search ArenaArena ratingtodaytoday	Nov 9todaytoday	#181,200	#61,228		#31,245best of the picked
MCP AtlasPass ratetodaytoday	Nov 9todaytoday	#2470.3%		#585.4%best of the picked
BFCLOverall accuracy · staletodaytoday	Nov 9todaytoday	#372.5%
Vision2
Vision ArenaArena ratingtodaytoday	Nov 9todaytoday	#121,289	#21,300best of the picked		#171,285
Document ArenaArena ratingtodaytoday	Nov 9todaytoday	#281,451			#111,477best of the picked
Speed1
AA SpeedOutput speedtodaytoday	Nov 9todaytoday		#260 tok/sbest of the picked		#1621 tok/s
Price1
AA PriceBlended pricetodaytoday	Nov 9todaytoday		#8$3.00best 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.