gpt-transcribe (openai) vs Qwen3.8 Max (0902) vs Muse Spark

• gpt-transcribe (openai)
• Qwen3.8 Max (0902)
• Muse Spark

Add a model

Add:Claude Fable 5.1Gemini 3.8 FlashKimi K3GLM-5.3

Head to head on 4 boards: Qwen3.8 Max (0902) places best on 3, Muse Spark places best on 1 and gpt-transcribe (openai) places best on 0. All 3 ranked on 0 of 14 boards.

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

gpt-transcribe (openai)Qwen3.8 Max (0902)Muse Spark

Board	Read	gpt-transcribe (openai)	Qwen3.8 Max (0902)	Muse Spark
Chat2
Text ArenaArena rating1dyesterday	Oct 61dyesterday		#201,482	#121,489best of the picked
MultiChallengeScore1dyesterday	Oct 61dyesterday			#175.5%
Reasoning5
GPQA DiamondAccuracy1dyesterday	Oct 61dyesterday		#2192.7%best of the picked	#4189.8%
Epoch ECIECI1dyesterday	Oct 61dyesterday		#22156.4best of the picked	#44152.0
HLEAccuracy1dyesterday	Oct 61dyesterday			#640.6%
AA IntelligenceIndex1dyesterday	Oct 61dyesterday		#1045.4
LiveBenchGlobal average1dyesterday	Oct 61dyesterday		#1578.5%
Coding1
WebDev ArenaArena rating1dyesterday	Oct 61dyesterday		#91,671
Agents and tools1
MCP AtlasPass rate1dyesterday	Oct 61dyesterday			#982.2%
Vision2
Vision ArenaArena rating1dyesterday	Oct 61dyesterday		#21,301best of the picked	#61,294
Document ArenaArena rating1dyesterday	Oct 61dyesterday			#241,444
Speech1
Open ASRAverage WER1dyesterday	Oct 61dyesterday	#204.57 WER
Speed1
AA SpeedOutput speed1dyesterday	Oct 61dyesterday		#2439 tok/s
Price1
AA PriceBlended price1dyesterday	Oct 61dyesterday		#14$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.