GPT Image 1.5 vs Claude Fable 5.1 vs Kimi K3.1 Pro

• GPT Image 1.5
• Claude Fable 5.1
• Kimi K3.1 Pro

Add a model

Add:Gemini 4 ArgonMuse Spark 1.1Qwen3.8 Max (0902)GLM-5.3

Head to head on 4 boards: Claude Fable 5.1 places best on 2, Kimi K3.1 Pro places best on 2 and GPT Image 1.5 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 Image 1.5Claude Fable 5.1Kimi K3.1 Pro

Board	Read	GPT Image 1.5	Claude Fable 5.1	Kimi K3.1 Pro
Chat1
Text ArenaArena rating1dyesterday	Oct 261dyesterday		#51,503
Reasoning5
AA IntelligenceIndex1dyesterday	Oct 261dyesterday		#553.4	#455.1best of the picked
LiveBenchGlobal average1dyesterday	Oct 261dyesterday		#183.4%
HLEAccuracy1dyesterday	Oct 261dyesterday		#246.5%
Epoch ECIECI1dyesterday	Oct 261dyesterday		#4166.5
ARC-AGI-2Score1dyesterday	Oct 261dyesterday		#790.0%
Coding2
WebDev ArenaArena rating1dyesterday	Oct 261dyesterday		#51,742best of the picked	#71,692
SWE-Bench ProResolved1dyesterday	Oct 261dyesterday		#292.2%
Agents and tools2
MCP AtlasPass rate1dyesterday	Oct 261dyesterday		#287.2%
Search ArenaArena rating1dyesterday	Oct 261dyesterday		#41,233
Vision2
Document ArenaArena rating1dyesterday	Oct 261dyesterday		#41,493
Vision ArenaArena rating1dyesterday	Oct 261dyesterday		#141,288
Image1
Image EditArena rating1dyesterday	Oct 261dyesterday	#161,367
Speed1
AA SpeedOutput speed1dyesterday	Oct 261dyesterday		#2470 tok/sbest of the picked	#3048 tok/s
Price1
AA PriceBlended price1dyesterday	Oct 261dyesterday		#31$20.0	#24$4.00best 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.