embeddinggemma-2 (google) vs Qwen3.8 Max (0902) vs Muse Spark 1.1 vs Kimi K3

Head to head on 7 boards: Kimi K3 places best on 3, Qwen3.8 Max (0902) places best on 2, Muse Spark 1.1 places best on 2 and embeddinggemma-2 (google) places best on 0. All 4 ranked on 0 of 16 boards.

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

embeddinggemma-2 (google)Qwen3.8 Max (0902)Muse Spark 1.1Kimi K3

Board	Read	embeddinggemma-2 (google)	Qwen3.8 Max (0902)	Muse Spark 1.1	Kimi K3
Chat2
Text ArenaArena ratingtodaytoday	Oct 29todaytoday		#211,482	#131,490best of the picked	#161,488
MultiChallengeScoretodaytoday	Oct 29todaytoday			#475.3%
Reasoning5
LiveBenchGlobal averagetodaytoday	Oct 29todaytoday		#1678.5%	#3575.3%	#1479.2%best of the picked
Epoch ECIECItodaytoday	Oct 29todaytoday		#21157.4	#43154.1	#19157.9best of the picked
GPQA DiamondAccuracytodaytoday	Oct 29todaytoday		#2492.7%		#2193.1%best of the picked
AA IntelligenceIndextodaytoday	Oct 29todaytoday		#1433.6
ARC-AGI-2Scoretodaytoday	Oct 29todaytoday				#3460.4%
Coding2
WebDev ArenaArena ratingtodaytoday	Oct 29todaytoday		#121,676best of the picked	#431,542	#151,656
SWE-Bench ProResolvedtodaytoday	Oct 29todaytoday				#688.2%
Agents and tools2
MCP AtlasPass ratetodaytoday	Oct 29todaytoday			#188.1%best of the picked	#882.3%
Search ArenaArena ratingtodaytoday	Oct 29todaytoday		#51,229
Vision2
Vision ArenaArena ratingtodaytoday	Oct 29todaytoday		#21,300best of the picked	#221,280
Document ArenaArena ratingtodaytoday	Oct 29todaytoday			#91,479
Embeddings1
MTEBMean task scoretodaytoday	Oct 29todaytoday	#3460.5%
Speed1
AA SpeedOutput speedtodaytoday	Oct 29todaytoday		#1541 tok/s
Price1
AA PriceBlended pricetodaytoday	Oct 29todaytoday		#6$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.