GPT-5 vs Qwen3.8 Max (0902) vs Claude Fable 5.1

• GPT-5
• Qwen3.8 Max (0902)
• Claude Fable 5.1

Add a model

Add:Gemini 4 ArgonMuse Spark 1.1?Inkling Small 2DeepSeek V4P1 Flash

Head to head on 12 boards: Claude Fable 5.1 places best on 7, Qwen3.8 Max (0902) places best on 5 and GPT-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.

GPT-5Qwen3.8 Max (0902)Claude Fable 5.1

Board	Read	GPT-5	Qwen3.8 Max (0902)	Claude Fable 5.1
Chat2
Text ArenaArena ratingtodaytoday	Nov 9todaytoday		#201,483	#61,504best of the picked
MultiChallengeScoretodaytoday	Nov 9todaytoday	#1363.2%
Reasoning7
Epoch ECIECItodaytoday	Nov 9todaytoday	#63150.0	#27157.4	#5166.9best of the picked
LiveBenchGlobal averagetodaytoday	Nov 9todaytoday		#1678.5%	#183.4%best of the picked
HLEAccuracytodaytoday	Nov 9todaytoday	#1525.3%		#246.5%best of the picked
ARC-AGI-2Scoretodaytoday	Nov 9todaytoday	#589.9%		#790.0%best of the picked
AA IntelligenceIndextodaytoday	Nov 9todaytoday		#1533.7	#950.0best of the picked
GPQA DiamondAccuracytodaytoday	Nov 9todaytoday	#7186.2%	#2692.7%best of the picked
MMLU-ProAccuracy · staletodaytoday	Nov 9todaytoday	#1687.1%
Coding4
WebDev ArenaArena ratingtodaytoday	Nov 9todaytoday	#771,417	#121,677	#51,746best of the picked
Aider PolyglotPass rate · staletodaytoday	Nov 9todaytoday	#188.0%
SWE-Bench ProResolvedtodaytoday	Nov 9todaytoday			#292.2%
SWE-bench VerifiedResolved · staletodaytoday	Nov 9todaytoday	#1665.0%
Agents and tools2
Search ArenaArena ratingtodaytoday	Nov 9todaytoday	#271,189	#61,228best of the picked	#71,227
MCP AtlasPass ratetodaytoday	Nov 9todaytoday			#387.2%
Vision2
Vision ArenaArena ratingtodaytoday	Nov 9todaytoday	#641,226	#21,300best of the picked	#131,288
Document ArenaArena ratingtodaytoday	Nov 9todaytoday			#21,499
Speed1
AA SpeedOutput speedtodaytoday	Nov 9todaytoday		#260 tok/sbest of the picked	#1422 tok/s
Price1
AA PriceBlended pricetodaytoday	Nov 9todaytoday		#8$3.00best of the picked	#17$20.0

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.