Mistral Large 4 High vs Gemini 3.8 Flash vs Muse Spark

• Mistral Large 4 High
• Gemini 3.8 Flash
• Muse Spark

Add a model

Add:Claude Fable 5.1GPT-6 AstraQwen3.8 Max (0902)Kimi K3

Head to head on 9 boards: Gemini 3.8 Flash places best on 8, Muse Spark places best on 1 and Mistral Large 4 High places best on 0. All 3 ranked on 0 of 16 boards.

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

Mistral Large 4 HighGemini 3.8 FlashMuse Spark

Board	Read	Mistral Large 4 High	Gemini 3.8 Flash	Muse Spark
Chat2
Text ArenaArena ratingtodaytoday	Oct 7todaytoday		#71,495best of the picked	#121,489
MultiChallengeScoretodaytoday	Oct 7todaytoday			#175.5%
Reasoning6
GPQA DiamondAccuracytodaytoday	Oct 7todaytoday		#395.4%best of the picked	#4189.8%
HLEAccuracytodaytoday	Oct 7todaytoday		#444.5%best of the picked	#640.6%
AA IntelligenceIndextodaytoday	Oct 7todaytoday	#2138.4	#1740.9best of the picked
Epoch ECIECItodaytoday	Oct 7todaytoday		#20156.7best of the picked	#44152.0
LiveBenchGlobal averagetodaytoday	Oct 7todaytoday	#4970.5%	#3275.8%best of the picked
ARC-AGI-2Scoretodaytoday	Oct 7todaytoday		#889.2%
Coding2
SWE-Bench ProResolvedtodaytoday	Oct 7todaytoday		#958.8%
WebDev ArenaArena ratingtodaytoday	Oct 7todaytoday		#251,583
Agents and tools1
MCP AtlasPass ratetodaytoday	Oct 7todaytoday			#982.2%
Vision2
Vision ArenaArena ratingtodaytoday	Oct 7todaytoday		#91,290	#61,294best of the picked
Document ArenaArena ratingtodaytoday	Oct 7todaytoday			#241,444
Speed1
AA SpeedOutput speedtodaytoday	Oct 7todaytoday	#10116 tok/s	#4216 tok/sbest of the picked
Price1
AA PriceBlended pricetodaytoday	Oct 7todaytoday	#14$2.06	#11$1.50best of the picked
Usage1
OpenRouterWeekly tokenstodaytoday	Oct 7todaytoday		#132.2T tok

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.