GPT-6.1 Terra vs Claude Fable 5.1 vs Kimi K3.1 Pro

• GPT-6.1 Terra
• 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: GPT-6.1 Terra places best on 2, Claude Fable 5.1 places best on 1 and Kimi K3.1 Pro places best on 1. All 3 ranked on 3 of 14 boards.

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

GPT-6.1 TerraClaude Fable 5.1Kimi K3.1 Pro

Board	Read	GPT-6.1 Terra	Claude Fable 5.1	Kimi K3.1 Pro
Chat1
Text ArenaArena rating1dyesterday	Oct 261dyesterday		#51,503
Reasoning5
AA IntelligenceIndex1dyesterday	Oct 261dyesterday	#1048.1	#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
Speed1
AA SpeedOutput speed1dyesterday	Oct 261dyesterday	#2091 tok/sbest of the picked	#2470 tok/s	#3048 tok/s
Price1
AA PriceBlended price1dyesterday	Oct 261dyesterday	#17$2.00best of the picked	#31$20.0	#24$4.00

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.