Inception vs Google vs DeepSeek vs OpenAI

Head to head on 26 boards: OpenAI places best on 14, Google places best on 11, Inception places best on 1 and DeepSeek places best on 1 (a tie counts for each). All 4 ranked on 1 of 28 boards.

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

InceptionGoogleDeepSeekOpenAI

Board	Read	Inception	Google	DeepSeek	OpenAI
Chat2
Text ArenaArena ratingtodaytoday	Oct 21todaytoday		#11,525best of the pickedGemini 4 Argon	#341,475DeepSeek V4.1 Flash	#171,485GPT-5.6 Sol
MultiChallengeScoretodaytoday	Oct 21todaytoday		#471.4%Gemini 3.1 Pro Preview	#2646.1%DeepSeek V3P1	#182.0%best of the pickedGPT-6.1 Sol
Reasoning7
GPQA DiamondAccuracytodaytoday	Oct 21todaytoday		#196.4%best of the pickedGemini 4 Argon	#2591.7%DeepSeek V4 Pro 0813	#295.8%GPT-6 Astra
ARC-AGI-2Scoretodaytoday	Oct 21todaytoday		#591.3%Gemini 4 Argon	#2172.9%DeepSeek V4.1 Flash	#195.0%best of the pickedGPT-6 Astra
MMLU-ProAccuracy · staletodaytoday	Oct 21todaytoday		#191.2%best of the pickedGemini 3.1 Pro Preview	#3385.0%DeepSeek-V3.2	#389.3%o1
Epoch ECIECItodaytoday	Oct 21todaytoday		#5166.4Gemini 4 Argon	#32155.9DeepSeek V4.1 Flash	#2168.8best of the pickedGPT-6 Astra
LiveBenchGlobal averagetodaytoday	Oct 21todaytoday		#1578.8%Gemini 3.7 Flash	#881.1%DeepSeek V4.1 Flash	#482.2%best of the pickedGPT-6 Astra
HLEAccuracytodaytoday	Oct 21todaytoday		#346.4%Gemini 3.1 Pro Preview		#154.8%best of the pickedGPT-6 Astra
AA IntelligenceIndextodaytoday	Oct 21todaytoday		#453.0best of the pickedGemini 4 Argon		#453.0best of the pickedGPT-6 Astra
Coding4
Aider PolyglotPass rate · staletodaytoday	Oct 21todaytoday		#383.1%Gemini 2.5 Pro (Jun 2025)	#874.2%DeepSeek-V3.2	#188.0%best of the pickedGPT-5
WebDev ArenaArena ratingtodaytoday	Oct 21todaytoday		#81,678Gemini 4 Argon	#191,619DeepSeek V4.1 Flash	#21,788best of the pickedGPT-6 Astra
SWE-bench VerifiedResolved · staletodaytoday	Oct 21todaytoday		#275.8%best of the pickedGemini 3 Flash	#1170.0%DeepSeek-V3.2	#672.8%GPT-5.2
SWE-Bench ProResolvedtodaytoday	Oct 21todaytoday		#392.2%best of the pickedGemini 4 Argon		#490.2%GPT-6 Astra
Agents and tools3
BFCLOverall accuracy · staletodaytoday	Oct 21todaytoday		#372.5%best of the pickedGemini 3 Pro	#1256.7%DeepSeek-V3.2	#763.0%o3
Search ArenaArena ratingtodaytoday	Oct 21todaytoday		#91,210Gemini 3.1 Pro Grounding		#11,257best of the pickedGPT-5.6 Sol
MCP AtlasPass ratetodaytoday	Oct 21todaytoday		#683.6%best of the pickedGemini 3.5 Flash		#1181.8%GPT-5.6
Vision2
Vision ArenaArena ratingtodaytoday	Oct 21todaytoday		#51,297best of the pickedGemini 3.7 Flash	#391,260DeepSeek V4.1 Flash	#61,294GPT-6.1 Sol
Document ArenaArena ratingtodaytoday	Oct 21todaytoday		#161,463Gemini 3.5 Flash		#61,486best of the pickedGPT-5.5
Image2
Text-to-ImageArena ratingtodaytoday	Oct 21todaytoday		#61,328Gemini Nano Banana 2.1		#11,425best of the pickedGPT Image 2.5 Sunburst
Image EditArena ratingtodaytoday	Oct 21todaytoday		#61,428Gemini Nano Banana 2.1		#11,524best of the pickedGPT Image 2.5 Sunburst
Video2
Text-to-VideoArena ratingtodaytoday	Oct 21todaytoday		#11,516best of the pickedGemini Omni 1.1 Flash		#111,368Sora 2 Pro
Image-to-VideoArena ratingtodaytoday	Oct 21todaytoday		#21,488Gemini Omni 1.1 Flash
Speech2
Speech ArenaArena ratingtodaytoday	Oct 21todaytoday		#51,278best of the pickedGemini 3.8 Flash TTS		#391,103TTS 1 Hd
Open ASRAverage WERtodaytoday	Oct 21todaytoday		#5911.65 WERgemma-4-E2B-it (google)		#306.38 WERbest of the pickedgpt-transcribe (openai)
Embeddings1
MTEBMean task scoretodaytoday	Oct 21todaytoday		#568.4%gemini-embedding-001 (google)
Speed1
AA SpeedOutput speedtodaytoday	Oct 21todaytoday	#3781 tok/sbest of the pickedMercury 2.5	#4454 tok/sGemini 3.5 Flash-Lite	#16209 tok/sDeepSeek V4.1 Flash	#9266 tok/sGPT OSS 20b
Price1
AA PriceBlended pricetodaytoday	Oct 21todaytoday		#13$1.50Gemini 3.8 Flash	#8$0.53DeepSeek V4.1 Flash	#3$0.20best of the pickedGPT-6 Luna
Usage1
OpenRouterWeekly tokenstodaytoday	Oct 21todaytoday			#127.3T tokbest of the pickedDeepSeek V4.1 Flash	#66.2T tokGPT-6 Luna

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.