GPT-5.4 vs Qwen3.8 Max (0902) vs Inkling Small 2

• GPT-5.4
• Qwen3.8 Max (0902)
• ?Inkling Small 2

Add a model

Add:Claude Fable 5.1Gemini 4 ArgonMuse Spark 1.1DeepSeek V4P1 Flash

Head to head on 8 boards: Qwen3.8 Max (0902) places best on 5, GPT-5.4 places best on 2 and Inkling Small 2 places best on 1. All 3 ranked on 0 of 16 boards.

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

GPT-5.4Qwen3.8 Max (0902)?Inkling Small 2

Board	Read	GPT-5.4	Qwen3.8 Max (0902)	?Inkling Small 2
Chat1
Text ArenaArena ratingtodaytoday	Nov 9todaytoday	#301,475	#201,483best of the picked
Reasoning7
LiveBenchGlobal averagetodaytoday	Nov 9todaytoday	#1878.0%	#1678.5%best of the picked
GPQA DiamondAccuracytodaytoday	Nov 9todaytoday	#2093.3%best of the picked	#2692.7%
Epoch ECIECItodaytoday	Nov 9todaytoday	#25157.8best of the picked	#27157.4
HLEAccuracytodaytoday	Nov 9todaytoday	#936.2%
MMLU-ProAccuracy · staletodaytoday	Nov 9todaytoday	#987.5%
AA IntelligenceIndextodaytoday	Nov 9todaytoday		#1533.7
ARC-AGI-2Scoretodaytoday	Nov 9todaytoday	#2374.0%
Coding2
WebDev ArenaArena ratingtodaytoday	Nov 9todaytoday	#651,463	#121,677best of the picked
SWE-Bench ProResolvedtodaytoday	Nov 9todaytoday			#986.3%
Agents and tools2
MCP AtlasPass ratetodaytoday	Nov 9todaytoday	#2370.6%		#585.4%best of the picked
Search ArenaArena ratingtodaytoday	Nov 9todaytoday	#211,196	#61,228best of the picked
Vision2
Vision ArenaArena ratingtodaytoday	Nov 9todaytoday	#191,282	#21,300best of the picked
Document ArenaArena ratingtodaytoday	Nov 9todaytoday	#141,471
Speed1
AA SpeedOutput speedtodaytoday	Nov 9todaytoday		#260 tok/s
Price1
AA PriceBlended pricetodaytoday	Nov 9todaytoday		#8$3.00

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.