GPT Image vs Qwen3.8 Max (0902) vs Kimi K3.1 Pro vs GLM-5.3

Head to head on 8 boards: Qwen3.8 Max (0902) places best on 4, Kimi K3.1 Pro places best on 2, GLM-5.3 places best on 2 and GPT Image places best on 0. All 4 ranked on 0 of 14 boards.

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

GPT ImageQwen3.8 Max (0902)Kimi K3.1 ProGLM-5.3

Board	Read	GPT Image	Qwen3.8 Max (0902)	Kimi K3.1 Pro	GLM-5.3
Chat1
Text ArenaArena rating1dyesterday	Oct 261dyesterday		#201,483best of the picked		#231,481
Reasoning4
AA IntelligenceIndex1dyesterday	Oct 261dyesterday		#1345.4	#455.1best of the picked	#1544.8
LiveBenchGlobal average1dyesterday	Oct 261dyesterday		#1678.5%best of the picked		#3176.1%
Epoch ECIECI1dyesterday	Oct 261dyesterday		#21157.4best of the picked		#31156.0
GPQA DiamondAccuracy1dyesterday	Oct 261dyesterday		#2392.7%best of the picked		#3190.9%
Coding2
WebDev ArenaArena rating1dyesterday	Oct 261dyesterday		#111,673	#71,692best of the picked	#221,623
SWE-Bench ProResolved1dyesterday	Oct 261dyesterday				#984.3%
Agents and tools2
MCP AtlasPass rate1dyesterday	Oct 261dyesterday				#584.2%
Search ArenaArena rating1dyesterday	Oct 261dyesterday		#51,229
Vision1
Vision ArenaArena rating1dyesterday	Oct 261dyesterday		#21,300
Image1
Image EditArena rating1dyesterday	Oct 261dyesterday	#141,387
Speed1
AA SpeedOutput speed1dyesterday	Oct 261dyesterday		#3241 tok/s	#3048 tok/s	#1994 tok/sbest of the picked
Price1
AA PriceBlended price1dyesterday	Oct 261dyesterday		#21$3.00	#24$4.00	#20$2.15best of the picked
Usage1
OpenRouterWeekly tokens1dyesterday	Oct 261dyesterday				#95.0T 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.