Claude Sonnet 5.5 vs Qwen3.8 Max (0902) vs Kimi K3

• Claude Sonnet 5.5
• Qwen3.8 Max (0902)
• Kimi K3

Add a model

Add:GPT-6 AstraGemini 3.8 FlashMuse SparkGLM-5.3

Head to head on 9 boards: Claude Sonnet 5.5 places best on 5, Qwen3.8 Max (0902) places best on 2 and Kimi K3 places best on 2. All 3 ranked on 8 of 13 boards.

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

Claude Sonnet 5.5Qwen3.8 Max (0902)Kimi K3

Board	Read	Claude Sonnet 5.5	Qwen3.8 Max (0902)	Kimi K3
Chat1
Text ArenaArena ratingtodaytoday	Oct 5todaytoday	#391,471	#201,482	#131,488best of the picked
Reasoning5
AA IntelligenceIndextodaytoday	Oct 5todaytoday	#256.0best of the picked	#1045.4	#1343.6
GPQA DiamondAccuracytodaytoday	Oct 5todaytoday	#295.6%best of the picked	#2192.7%	#1893.1%
Epoch ECIECItodaytoday	Oct 5todaytoday	#3165.2best of the picked	#20156.6	#13157.6
LiveBenchGlobal averagetodaytoday	Oct 5todaytoday	#2077.8%	#1578.5%	#1379.2%best of the picked
ARC-AGI-2Scoretodaytoday	Oct 5todaytoday			#2960.4%
Coding2
WebDev ArenaArena ratingtodaytoday	Oct 5todaytoday	#31,786best of the picked	#91,671	#101,658
SWE-Bench ProResolvedtodaytoday	Oct 5todaytoday			#488.2%
Agents and tools1
MCP AtlasPass ratetodaytoday	Oct 5todaytoday			#882.3%
Vision1
Vision ArenaArena ratingtodaytoday	Oct 5todaytoday	#291,268	#21,301best of the picked
Speed1
AA SpeedOutput speedtodaytoday	Oct 5todaytoday	#5139 tok/sbest of the picked	#2439 tok/s	#2536 tok/s
Price1
AA PriceBlended pricetodaytoday	Oct 5todaytoday	#17$4.00	#14$3.00best of the picked	#22$6.00
Usage1
OpenRouterWeekly tokenstodaytoday	Oct 5todaytoday			#151.6T 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.