JT-35B-Flash vs Muse Spark vs Qwen3.8 Max (0902) vs Gemini 3.8 Flash

Head to head on 10 boards: Gemini 3.8 Flash places best on 6, Qwen3.8 Max (0902) places best on 4, JT-35B-Flash places best on 0 and Muse Spark places best on 0. All 4 ranked on 0 of 16 boards.

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

CMJT-35B-FlashMuse SparkQwen3.8 Max (0902)Gemini 3.8 Flash

Board	Read	CMJT-35B-Flash	Muse Spark	Qwen3.8 Max (0902)	Gemini 3.8 Flash
Chat2
Text ArenaArena rating1dyesterday	Oct 61dyesterday		#121,489	#201,482	#71,495best of the picked
MultiChallengeScore1dyesterday	Oct 61dyesterday		#175.5%
Reasoning6
GPQA DiamondAccuracy1dyesterday	Oct 61dyesterday		#4189.8%	#2192.7%	#395.4%best of the picked
AA IntelligenceIndex1dyesterday	Oct 61dyesterday	#5818.7		#1045.4best of the picked	#1640.9
Epoch ECIECI1dyesterday	Oct 61dyesterday		#44152.0	#22156.4	#20156.7best of the picked
HLEAccuracy1dyesterday	Oct 61dyesterday		#640.6%		#444.5%best of the picked
LiveBenchGlobal average1dyesterday	Oct 61dyesterday			#1578.5%best of the picked	#3275.8%
ARC-AGI-2Score1dyesterday	Oct 61dyesterday				#889.2%
Coding2
WebDev ArenaArena rating1dyesterday	Oct 61dyesterday			#91,671best of the picked	#251,583
SWE-Bench ProResolved1dyesterday	Oct 61dyesterday				#958.8%
Agents and tools1
MCP AtlasPass rate1dyesterday	Oct 61dyesterday		#982.2%
Vision2
Vision ArenaArena rating1dyesterday	Oct 61dyesterday		#61,294	#21,301best of the picked	#91,290
Document ArenaArena rating1dyesterday	Oct 61dyesterday		#241,444
Speed1
AA SpeedOutput speed1dyesterday	Oct 61dyesterday			#2439 tok/s	#1249 tok/sbest of the picked
Price1
AA PriceBlended price1dyesterday	Oct 61dyesterday			#14$3.00	#10$1.50best of the picked
Usage1
OpenRouterWeekly tokens1dyesterday	Oct 61dyesterday				#132.2T tok

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.