Motif 3 vs Muse Spark 1.3 vs Qwen3.8 Max (0902) vs GPT-6 Astra

Head to head on 10 boards: GPT-6 Astra places best on 5, Muse Spark 1.3 places best on 4, Qwen3.8 Max (0902) places best on 1 and Motif 3 places best on 0. All 4 ranked on 1 of 13 boards.

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

MTMotif 3Muse Spark 1.3Qwen3.8 Max (0902)GPT-6 Astra

Board	Read	MTMotif 3	Muse Spark 1.3	Qwen3.8 Max (0902)	GPT-6 Astra
Chat1
Text ArenaArena ratingtodaytoday	Sep 27todaytoday		#71,494best of the picked	#221,479	#231,478
Reasoning6
AA IntelligenceIndextodaytoday	Sep 27todaytoday	#2433.6	#448.1	#845.4	#352.7best of the picked
Epoch ECIECItodaytoday	Sep 27todaytoday		#15156.9	#17156.7	#1166.6best of the picked
LiveBenchGlobal averagetodaytoday	Sep 27todaytoday		#581.6%	#1478.5%	#482.2%best of the picked
GPQA DiamondAccuracytodaytoday	Sep 27todaytoday			#1792.7%	#195.8%best of the picked
HLEAccuracytodaytoday	Sep 27todaytoday				#154.8%
ARC-AGI-2Scoretodaytoday	Sep 27todaytoday				#195.0%
Coding2
WebDev ArenaArena ratingtodaytoday	Sep 27todaytoday		#81,656	#61,672	#21,792best of the picked
SWE-Bench ProResolvedtodaytoday	Sep 27todaytoday				#390.2%
Vision2
Vision ArenaArena ratingtodaytoday	Sep 27todaytoday		#51,294	#21,302best of the picked	#141,284
Document ArenaArena ratingtodaytoday	Sep 27todaytoday		#121,471best of the picked		#131,468
Speed1
AA SpeedOutput speedtodaytoday	Sep 27todaytoday		#2232 tok/sbest of the picked	#2239 tok/s	#1763 tok/s
Price1
AA PriceBlended pricetodaytoday	Sep 27todaytoday		#11$2.00best of the picked	#13$3.00	#23$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.