gpt-transcribe (openai) vs Qwen3.8 Max (0902) vs Claude Fable 5.1

• gpt-transcribe (openai)
• Qwen3.8 Max (0902)
• Claude Fable 5.1

Add a model

Add:Gemini 3.8 FlashMuse SparkKimi K3GLM-5.3

Head to head on 8 boards: Claude Fable 5.1 places best on 6, Qwen3.8 Max (0902) places best on 2 and gpt-transcribe (openai) places best on 0. All 3 ranked on 0 of 15 boards.

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

gpt-transcribe (openai)Qwen3.8 Max (0902)Claude Fable 5.1

Board	Read	gpt-transcribe (openai)	Qwen3.8 Max (0902)	Claude Fable 5.1
Chat1
Text ArenaArena rating1dyesterday	Oct 61dyesterday		#201,482	#61,501best of the picked
Reasoning6
LiveBenchGlobal average1dyesterday	Oct 61dyesterday		#1578.5%	#183.4%best of the picked
AA IntelligenceIndex1dyesterday	Oct 61dyesterday		#1045.4	#353.4best of the picked
Epoch ECIECI1dyesterday	Oct 61dyesterday		#22156.4	#5164.7best of the picked
HLEAccuracy1dyesterday	Oct 61dyesterday			#246.5%
ARC-AGI-2Score1dyesterday	Oct 61dyesterday			#690.0%
GPQA DiamondAccuracy1dyesterday	Oct 61dyesterday		#2192.7%
Coding2
WebDev ArenaArena rating1dyesterday	Oct 61dyesterday		#91,671	#51,749best of the picked
SWE-Bench ProResolved1dyesterday	Oct 61dyesterday			#292.2%
Agents and tools1
MCP AtlasPass rate1dyesterday	Oct 61dyesterday			#287.2%
Vision2
Vision ArenaArena rating1dyesterday	Oct 61dyesterday		#21,301best of the picked	#131,288
Document ArenaArena rating1dyesterday	Oct 61dyesterday			#21,513
Speech1
Open ASRAverage WER1dyesterday	Oct 61dyesterday	#204.57 WER
Speed1
AA SpeedOutput speed1dyesterday	Oct 61dyesterday		#2439 tok/s	#1568 tok/sbest of the picked
Price1
AA PriceBlended price1dyesterday	Oct 61dyesterday		#14$3.00best of the picked	#24$20.0

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.