gpt-transcribe (openai) vs Gemini 3.8 Flash vs Kimi K3

• gpt-transcribe (openai)
• Gemini 3.8 Flash
• Kimi K3

Add a model

Add:Claude Fable 5.1Muse SparkQwen3.8 Max (0902)GLM-5.3

Head to head on 11 boards: Gemini 3.8 Flash places best on 6, Kimi K3 places best on 5 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)Gemini 3.8 FlashKimi K3

Board	Read	gpt-transcribe (openai)	Gemini 3.8 Flash	Kimi K3
Chat1
Text ArenaArena rating1dyesterday	Oct 61dyesterday		#71,495best of the picked	#131,488
Reasoning6
GPQA DiamondAccuracy1dyesterday	Oct 61dyesterday		#395.4%best of the picked	#1893.1%
ARC-AGI-2Score1dyesterday	Oct 61dyesterday		#889.2%best of the picked	#2960.4%
AA IntelligenceIndex1dyesterday	Oct 61dyesterday		#1640.9	#1343.6best of the picked
LiveBenchGlobal average1dyesterday	Oct 61dyesterday		#3275.8%	#1379.2%best of the picked
Epoch ECIECI1dyesterday	Oct 61dyesterday		#20156.7	#15157.4best of the picked
HLEAccuracy1dyesterday	Oct 61dyesterday		#444.5%
Coding2
SWE-Bench ProResolved1dyesterday	Oct 61dyesterday		#958.8%	#488.2%best of the picked
WebDev ArenaArena rating1dyesterday	Oct 61dyesterday		#251,583	#101,658best of the picked
Agents and tools1
MCP AtlasPass rate1dyesterday	Oct 61dyesterday			#882.3%
Vision1
Vision ArenaArena rating1dyesterday	Oct 61dyesterday		#91,290
Speech1
Open ASRAverage WER1dyesterday	Oct 61dyesterday	#204.57 WER
Speed1
AA SpeedOutput speed1dyesterday	Oct 61dyesterday		#1249 tok/sbest of the picked	#2536 tok/s
Price1
AA PriceBlended price1dyesterday	Oct 61dyesterday		#10$1.50best of the picked	#22$6.00
Usage1
OpenRouterWeekly tokens1dyesterday	Oct 61dyesterday		#132.2T tokbest of the picked	#151.7T 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.