Gemini 2.5 Pro (Jun 2025) vs Muse Spark 1.1 vs Qwen3.8 Max (0902)

One row per board where at least one is ranked, from each board's current capture.

Gemini 2.5 Pro (Jun 2025)
Muse Spark 1.1
Qwen3.8 Max (0902)

Add:

GPT-6 Astra

Claude Fable 5.1 Inkling Small 2

DeepSeek V4P1 Flash

Head to head on 9 boards: Qwen3.8 Max (0902) places best on 6, Muse Spark 1.1 places best on 3 and Gemini 2.5 Pro (Jun 2025) places best on 0. All 3 ranked on 3 of 19 boards.

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

Board	Read	Gemini 2.5 Pro (Jun 2025)	Muse Spark 1.1	Qwen3.8 Max (0902)
Chat2
Text ArenaArena ratingyesterday	Nov 9yesterday	#731,445	#131,490best of the picked	#201,483
MultiChallengeScoreyesterday	Nov 9yesterday	#2653.6%	#475.3%best of the picked
Reasoning7
Epoch ECIECIyesterday	Nov 9yesterday	#88144.8	#42154.9	#27157.4best of the picked
LiveBenchGlobal averageyesterday	Nov 9yesterday		#3575.3%	#1678.5%best of the picked
GPQA DiamondAccuracyyesterday	Nov 9yesterday	#7685.3%		#2692.7%best of the picked
AA IntelligenceIndexyesterday	Nov 9yesterday			#1533.7
HLEAccuracyyesterday	Nov 9yesterday	#1921.6%
MMLU-ProAccuracy · staleyesterday	Nov 9yesterday	#2986.0%
ARC-AGI-2Scoreyesterday	Nov 9yesterday	#644.9%
Coding3
WebDev ArenaArena ratingyesterday	Nov 9yesterday		#441,542	#121,677best of the picked
Aider PolyglotPass rate · staleyesterday	Nov 9yesterday	#383.1%
SWE-bench VerifiedResolved · staleyesterday	Nov 9yesterday	#2753.6%
Agents and tools2
Search ArenaArena ratingyesterday	Nov 9yesterday	#361,144		#61,228best of the picked
MCP AtlasPass rateyesterday	Nov 9yesterday		#288.1%
Vision2
Vision ArenaArena ratingyesterday	Nov 9yesterday	#501,248	#241,279	#21,300best of the picked
Document ArenaArena ratingyesterday	Nov 9yesterday	#361,432	#91,479best of the picked
Speech1
Speech ArenaArena ratingyesterday	Nov 9yesterday	#741,040
Speed1
AA SpeedOutput speedyesterday	Nov 9yesterday			#260 tok/s
Price1
AA PriceBlended priceyesterday	Nov 9yesterday			#8$3.00

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.

More comparisons