e5-base-v2 (intfloat) vs Claude Fable 5.1 vs Muse Spark

• Ie5-base-v2 (intfloat)
• Claude Fable 5.1
• Muse Spark

Add a model

Add:GPT-6 AstraGemini 3.8 FlashQwen3.8 Max (0902)Kimi K3

Head to head on 6 boards: Claude Fable 5.1 places best on 5, Muse Spark places best on 1 and e5-base-v2 (intfloat) 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.

Ie5-base-v2 (intfloat)Claude Fable 5.1Muse Spark

Board	Read	Ie5-base-v2 (intfloat)	Claude Fable 5.1	Muse Spark
Chat2
Text ArenaArena ratingtodaytoday	Oct 5todaytoday		#61,501best of the picked	#121,489
MultiChallengeScoretodaytoday	Oct 5todaytoday			#175.5%
Reasoning6
HLEAccuracytodaytoday	Oct 5todaytoday		#246.5%best of the picked	#640.6%
Epoch ECIECItodaytoday	Oct 5todaytoday		#4164.8best of the picked	#40152.1
LiveBenchGlobal averagetodaytoday	Oct 5todaytoday		#183.4%
AA IntelligenceIndextodaytoday	Oct 5todaytoday		#353.4
ARC-AGI-2Scoretodaytoday	Oct 5todaytoday		#690.0%
GPQA DiamondAccuracytodaytoday	Oct 5todaytoday			#4189.8%
Coding2
SWE-Bench ProResolvedtodaytoday	Oct 5todaytoday		#292.2%
WebDev ArenaArena ratingtodaytoday	Oct 5todaytoday		#51,749
Agents and tools1
MCP AtlasPass ratetodaytoday	Oct 5todaytoday		#287.2%best of the picked	#982.2%
Vision2
Document ArenaArena ratingtodaytoday	Oct 5todaytoday		#21,513best of the picked	#241,444
Vision ArenaArena ratingtodaytoday	Oct 5todaytoday		#131,288	#61,294best of the picked
Embeddings1
MTEBMean task scoretodaytoday	Oct 5todaytoday	#6246.0%
Speed1
AA SpeedOutput speedtodaytoday	Oct 5todaytoday		#1568 tok/s
Price1
AA PriceBlended pricetodaytoday	Oct 5todaytoday		#24$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.