embeddinggemma-2 (google) vs Claude Fable 5.1 vs Kimi K3

• embeddinggemma-2 (google)
• Claude Fable 5.1
• Kimi K3

Add a model

Add:GPT-6 AstraMuse Spark 1.1Qwen3.8 Max (0902)GLM-5.3

Head to head on 7 boards: Claude Fable 5.1 places best on 7, embeddinggemma-2 (google) places best on 0 and Kimi K3 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.

embeddinggemma-2 (google)Claude Fable 5.1Kimi K3

Board	Read	embeddinggemma-2 (google)	Claude Fable 5.1	Kimi K3
Chat1
Text ArenaArena ratingtodaytoday	Oct 29todaytoday		#51,504best of the picked	#161,488
Reasoning6
LiveBenchGlobal averagetodaytoday	Oct 29todaytoday		#183.4%best of the picked	#1479.2%
Epoch ECIECItodaytoday	Oct 29todaytoday		#4166.5best of the picked	#19157.9
ARC-AGI-2Scoretodaytoday	Oct 29todaytoday		#790.0%best of the picked	#3460.4%
HLEAccuracytodaytoday	Oct 29todaytoday		#246.5%
AA IntelligenceIndextodaytoday	Oct 29todaytoday		#949.7
GPQA DiamondAccuracytodaytoday	Oct 29todaytoday			#2193.1%
Coding2
SWE-Bench ProResolvedtodaytoday	Oct 29todaytoday		#292.2%best of the picked	#688.2%
WebDev ArenaArena ratingtodaytoday	Oct 29todaytoday		#61,746best of the picked	#151,656
Agents and tools2
MCP AtlasPass ratetodaytoday	Oct 29todaytoday		#287.2%best of the picked	#882.3%
Search ArenaArena ratingtodaytoday	Oct 29todaytoday		#41,233
Vision2
Document ArenaArena ratingtodaytoday	Oct 29todaytoday		#41,493
Vision ArenaArena ratingtodaytoday	Oct 29todaytoday		#141,288
Embeddings1
MTEBMean task scoretodaytoday	Oct 29todaytoday	#3460.5%
Speed1
AA SpeedOutput speedtodaytoday	Oct 29todaytoday		#1467 tok/s
Price1
AA PriceBlended pricetodaytoday	Oct 29todaytoday		#15$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.