Polly vs Gemini 3.8 Flash vs Claude Fable 5.1

• Polly
• Gemini 3.8 Flash
• Claude Fable 5.1

Add a model

Add:GPT-6 AstraMuse Spark 1.3Qwen3.8 Max (0902)Kimi K3

Head to head on 10 boards: Claude Fable 5.1 places best on 8, Gemini 3.8 Flash places best on 2 and Polly 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.

PollyGemini 3.8 FlashClaude Fable 5.1

Board	Read	Polly	Gemini 3.8 Flash	Claude Fable 5.1
Chat1
Text ArenaArena ratingtodaytoday	Sep 27todaytoday		#81,492	#51,501best of the picked
Reasoning6
LiveBenchGlobal averagetodaytoday	Sep 27todaytoday		#3175.8%	#183.4%best of the picked
AA IntelligenceIndextodaytoday	Sep 27todaytoday		#1540.9	#253.4best of the picked
HLEAccuracytodaytoday	Sep 27todaytoday		#444.5%	#246.5%best of the picked
Epoch ECIECItodaytoday	Sep 27todaytoday		#13157.1	#2165.0best of the picked
ARC-AGI-2Scoretodaytoday	Sep 27todaytoday		#689.2%	#590.0%best of the picked
GPQA DiamondAccuracytodaytoday	Sep 27todaytoday		#295.4%
Coding2
SWE-Bench ProResolvedtodaytoday	Sep 27todaytoday		#958.8%	#292.2%best of the picked
WebDev ArenaArena ratingtodaytoday	Sep 27todaytoday		#251,580	#31,751best of the picked
Agents and tools1
MCP AtlasPass ratetodaytoday	Sep 27todaytoday			#287.2%
Vision2
Document ArenaArena ratingtodaytoday	Sep 27todaytoday			#21,513
Vision ArenaArena ratingtodaytoday	Sep 27todaytoday			#91,289
Speech1
Speech ArenaArena ratingtodaytoday	Sep 27todaytoday	#90829
Speed1
AA SpeedOutput speedtodaytoday	Sep 27todaytoday		#1308 tok/sbest of the picked	#1569 tok/s
Price1
AA PriceBlended pricetodaytoday	Sep 27todaytoday		#9$1.50best of the picked	#23$20.0
Usage1
OpenRouterWeekly tokenstodaytoday	Sep 27todaytoday		#142.2T 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.