gpt-transcribe (openai) vs Muse Spark vs Kimi K3 vs GLM-5.3

Head to head on 11 boards: Kimi K3 places best on 5, GLM-5.3 places best on 5, Muse Spark places best on 1 and gpt-transcribe (openai) places best on 0. All 4 ranked on 0 of 17 boards.

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

gpt-transcribe (openai)Muse SparkKimi K3GLM-5.3

Board	Read	gpt-transcribe (openai)	Muse Spark	Kimi K3	GLM-5.3
Chat2
Text ArenaArena rating1dyesterday	Oct 61dyesterday		#121,489best of the picked	#131,488	#241,478
MultiChallengeScore1dyesterday	Oct 61dyesterday		#175.5%
Reasoning6
Epoch ECIECI1dyesterday	Oct 61dyesterday		#44152.0	#15157.4best of the picked	#27155.6
GPQA DiamondAccuracy1dyesterday	Oct 61dyesterday		#4189.8%	#1893.1%best of the picked	#2990.9%
AA IntelligenceIndex1dyesterday	Oct 61dyesterday			#1343.6	#1144.8best of the picked
LiveBenchGlobal average1dyesterday	Oct 61dyesterday			#1379.2%best of the picked	#3076.1%
HLEAccuracy1dyesterday	Oct 61dyesterday		#640.6%
ARC-AGI-2Score1dyesterday	Oct 61dyesterday			#2960.4%
Coding2
SWE-Bench ProResolved1dyesterday	Oct 61dyesterday			#488.2%best of the picked	#784.3%
WebDev ArenaArena rating1dyesterday	Oct 61dyesterday			#101,658best of the picked	#161,623
Agents and tools1
MCP AtlasPass rate1dyesterday	Oct 61dyesterday		#982.2%	#882.3%	#584.2%best of the picked
Vision2
Vision ArenaArena rating1dyesterday	Oct 61dyesterday		#61,294
Document ArenaArena rating1dyesterday	Oct 61dyesterday		#241,444
Speech1
Open ASRAverage WER1dyesterday	Oct 61dyesterday	#204.57 WER
Speed1
AA SpeedOutput speed1dyesterday	Oct 61dyesterday			#2536 tok/s	#1471 tok/sbest of the picked
Price1
AA PriceBlended price1dyesterday	Oct 61dyesterday			#22$6.00	#13$2.15best of the picked
Usage1
OpenRouterWeekly tokens1dyesterday	Oct 61dyesterday			#151.7T tok	#113.0T tokbest of the picked

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.