Claude Opus 4.5 vs Qwen3.8 Max (0902) vs Gemini 4 Argon

• Claude Opus 4.5
• Qwen3.8 Max (0902)
• Gemini 4 Argon

Add a model

Add:GPT-6 AstraMuse Spark 1.1?Inkling Small 2DeepSeek V4P1 Flash

Head to head on 12 boards: Gemini 4 Argon places best on 8, Qwen3.8 Max (0902) places best on 4 and Claude Opus 4.5 places best on 0. All 3 ranked on 4 of 19 boards.

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

Claude Opus 4.5Qwen3.8 Max (0902)Gemini 4 Argon

Board	Read	Claude Opus 4.5	Qwen3.8 Max (0902)	Gemini 4 Argon
Chat2
Text ArenaArena ratingtodaytoday	Nov 9todaytoday	#361,474	#201,483	#21,523best of the picked
MultiChallengeScoretodaytoday	Nov 9todaytoday	#1859.0%		#278.7%best of the picked
Reasoning7
GPQA DiamondAccuracytodaytoday	Nov 9todaytoday	#7286.0%	#2692.7%	#196.4%best of the picked
Epoch ECIECItodaytoday	Nov 9todaytoday	#55151.8	#27157.4	#6166.4best of the picked
ARC-AGI-2Scoretodaytoday	Nov 9todaytoday	#4537.6%		#591.3%best of the picked
AA IntelligenceIndextodaytoday	Nov 9todaytoday		#1533.7	#750.4best of the picked
LiveBenchGlobal averagetodaytoday	Nov 9todaytoday	#4672.6%	#1678.5%best of the picked
MMLU-ProAccuracy · staletodaytoday	Nov 9todaytoday	#1287.3%
HLEAccuracytodaytoday	Nov 9todaytoday	#1625.2%
Coding3
WebDev ArenaArena ratingtodaytoday	Nov 9todaytoday	#591,494	#121,677	#101,683best of the picked
SWE-bench VerifiedResolved · staletodaytoday	Nov 9todaytoday	#176.8%
SWE-Bench ProResolvedtodaytoday	Nov 9todaytoday			#392.2%
Agents and tools3
MCP AtlasPass ratetodaytoday	Nov 9todaytoday	#2569.8%		#190.7%best of the picked
Search ArenaArena ratingtodaytoday	Nov 9todaytoday	#291,186	#61,228best of the picked
BFCLOverall accuracy · staletodaytoday	Nov 9todaytoday	#177.5%
Vision2
Vision ArenaArena ratingtodaytoday	Nov 9todaytoday		#21,300
Document ArenaArena ratingtodaytoday	Nov 9todaytoday	#181,468
Speed1
AA SpeedOutput speedtodaytoday	Nov 9todaytoday		#260 tok/sbest of the picked	#1028 tok/s
Price1
AA PriceBlended pricetodaytoday	Nov 9todaytoday		#8$3.00best of the picked	#13$8.00

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.