Soundsgoodai vs OpenAI vs DeepSeek vs Google

Head to head on 26 boards: OpenAI places best on 13, Google places best on 12, Soundsgoodai places best on 1 and DeepSeek places best on 1 (a tie counts for each). All 4 ranked on 0 of 28 boards.

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

SSoundsgoodaiOpenAIDeepSeekGoogle

Board	Read	SSoundsgoodai	OpenAI	DeepSeek	Google
Chat2
Text ArenaArena ratingtodaytoday	Oct 21todaytoday		#171,485GPT-5.6 Sol	#341,475DeepSeek V4.1 Flash	#11,525best of the pickedGemini 4 Argon
MultiChallengeScoretodaytoday	Oct 21todaytoday		#182.0%best of the pickedGPT-6.1 Sol	#2646.1%DeepSeek V3P1	#471.4%Gemini 3.1 Pro Preview
Reasoning7
GPQA DiamondAccuracytodaytoday	Oct 21todaytoday		#295.8%GPT-6 Astra	#2591.7%DeepSeek V4 Pro 0813	#196.4%best of the pickedGemini 4 Argon
ARC-AGI-2Scoretodaytoday	Oct 21todaytoday		#195.0%best of the pickedGPT-6 Astra	#2172.9%DeepSeek V4.1 Flash	#591.3%Gemini 4 Argon
MMLU-ProAccuracy · staletodaytoday	Oct 21todaytoday		#389.3%o1	#3385.0%DeepSeek-V3.2	#191.2%best of the pickedGemini 3.1 Pro Preview
Epoch ECIECItodaytoday	Oct 21todaytoday		#2168.8best of the pickedGPT-6 Astra	#32155.9DeepSeek V4.1 Flash	#5166.4Gemini 4 Argon
LiveBenchGlobal averagetodaytoday	Oct 21todaytoday		#482.2%best of the pickedGPT-6 Astra	#881.1%DeepSeek V4.1 Flash	#1578.8%Gemini 3.7 Flash
HLEAccuracytodaytoday	Oct 21todaytoday		#154.8%best of the pickedGPT-6 Astra		#346.4%Gemini 3.1 Pro Preview
AA IntelligenceIndextodaytoday	Oct 21todaytoday		#453.0best of the pickedGPT-6 Astra		#453.0best of the pickedGemini 4 Argon
Coding4
Aider PolyglotPass rate · staletodaytoday	Oct 21todaytoday		#188.0%best of the pickedGPT-5	#874.2%DeepSeek-V3.2	#383.1%Gemini 2.5 Pro (Jun 2025)
WebDev ArenaArena ratingtodaytoday	Oct 21todaytoday		#21,788best of the pickedGPT-6 Astra	#191,619DeepSeek V4.1 Flash	#81,678Gemini 4 Argon
SWE-bench VerifiedResolved · staletodaytoday	Oct 21todaytoday		#672.8%GPT-5.2	#1170.0%DeepSeek-V3.2	#275.8%best of the pickedGemini 3 Flash
SWE-Bench ProResolvedtodaytoday	Oct 21todaytoday		#490.2%GPT-6 Astra		#392.2%best of the pickedGemini 4 Argon
Agents and tools3
BFCLOverall accuracy · staletodaytoday	Oct 21todaytoday		#763.0%o3	#1256.7%DeepSeek-V3.2	#372.5%best of the pickedGemini 3 Pro
Search ArenaArena ratingtodaytoday	Oct 21todaytoday		#11,257best of the pickedGPT-5.6 Sol		#91,210Gemini 3.1 Pro Grounding
MCP AtlasPass ratetodaytoday	Oct 21todaytoday		#1181.8%GPT-5.6		#683.6%best of the pickedGemini 3.5 Flash
Vision2
Vision ArenaArena ratingtodaytoday	Oct 21todaytoday		#61,294GPT-6.1 Sol	#391,260DeepSeek V4.1 Flash	#51,297best of the pickedGemini 3.7 Flash
Document ArenaArena ratingtodaytoday	Oct 21todaytoday		#61,486best of the pickedGPT-5.5		#161,463Gemini 3.5 Flash
Image2
Text-to-ImageArena ratingtodaytoday	Oct 21todaytoday		#11,425best of the pickedGPT Image 2.5 Sunburst		#61,328Gemini Nano Banana 2.1
Image EditArena ratingtodaytoday	Oct 21todaytoday		#11,524best of the pickedGPT Image 2.5 Sunburst		#61,428Gemini Nano Banana 2.1
Video2
Text-to-VideoArena ratingtodaytoday	Oct 21todaytoday		#111,368Sora 2 Pro		#11,516best of the pickedGemini Omni 1.1 Flash
Image-to-VideoArena ratingtodaytoday	Oct 21todaytoday				#21,488Gemini Omni 1.1 Flash
Speech2
Open ASRAverage WERtodaytoday	Oct 21todaytoday	#246.22 WERbest of the pickedZipformer-cr-ctc-transducer-XL-290M (fast-gpu-asr, transducer modified beam search) (soundsgoodai)	#306.38 WERgpt-transcribe (openai)		#5911.65 WERgemma-4-E2B-it (google)
Speech ArenaArena ratingtodaytoday	Oct 21todaytoday		#391,103TTS 1 Hd		#51,278best of the pickedGemini 3.8 Flash TTS
Embeddings1
MTEBMean task scoretodaytoday	Oct 21todaytoday				#568.4%gemini-embedding-001 (google)
Speed1
AA SpeedOutput speedtodaytoday	Oct 21todaytoday		#9266 tok/sGPT OSS 20b	#16209 tok/sDeepSeek V4.1 Flash	#4454 tok/sbest of the pickedGemini 3.5 Flash-Lite
Price1
AA PriceBlended pricetodaytoday	Oct 21todaytoday		#3$0.20best of the pickedGPT-6 Luna	#8$0.53DeepSeek V4.1 Flash	#13$1.50Gemini 3.8 Flash
Usage1
OpenRouterWeekly tokenstodaytoday	Oct 21todaytoday		#66.2T tokGPT-6 Luna	#127.3T tokbest of the pickedDeepSeek V4.1 Flash

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.