Edge0 vs Google vs OpenAI vs DeepSeek

Head to head on 26 boards: OpenAI places best on 15, Google places best on 8, DeepSeek places best on 2 and Edge0 places best on 1. All 4 ranked on 0 of 28 boards.

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

EEdge0GoogleOpenAIDeepSeek

Board	Read	EEdge0	Google	OpenAI	DeepSeek
Chat2
Text ArenaArena ratingtodaytoday	Oct 8todaytoday		#11,525best of the pickedGemini 4 Argon	#171,484GPT-5.6 Sol	#321,474DeepSeek V4.1 Flash
MultiChallengeScoretodaytoday	Oct 8todaytoday		#471.4%Gemini 3.1 Pro Preview	#182.0%best of the pickedGPT-6.1 Sol	#2546.1%DeepSeek V3P1
Reasoning7
GPQA DiamondAccuracytodaytoday	Oct 8todaytoday		#395.4%Gemini 3.8 Flash	#195.8%best of the pickedGPT-6 Astra	#2491.7%DeepSeek V4 Pro 0813
ARC-AGI-2Scoretodaytoday	Oct 8todaytoday		#889.2%Gemini 3.8 Flash	#195.0%best of the pickedGPT-6 Astra	#2072.9%DeepSeek V4.1 Flash
MMLU-ProAccuracy · staletodaytoday	Oct 8todaytoday		#191.2%best of the pickedGemini 3.1 Pro Preview	#389.3%o1	#3385.0%DeepSeek-V3.2
Epoch ECIECItodaytoday	Oct 8todaytoday		#16157.3Gemini 3.7 Flash	#2166.4best of the pickedGPT-6 Astra	#29155.3DeepSeek V4 Pro 0813
AA IntelligenceIndextodaytoday	Oct 8todaytoday		#552.6Gemini 4 Argon	#452.7best of the pickedGPT-6 Astra	#2139.5DeepSeek V4.1 Flash
LiveBenchGlobal averagetodaytoday	Oct 8todaytoday		#1478.8%Gemini 3.7 Flash	#482.2%best of the pickedGPT-6 Astra	#781.1%DeepSeek V4.1 Flash
HLEAccuracytodaytoday	Oct 8todaytoday		#346.4%Gemini 3.1 Pro Preview	#154.8%best of the pickedGPT-6 Astra
Coding4
Aider PolyglotPass rate · staletodaytoday	Oct 8todaytoday		#383.1%Gemini 2.5 Pro (Jun 2025)	#188.0%best of the pickedGPT-5	#874.2%DeepSeek-V3.2
WebDev ArenaArena ratingtodaytoday	Oct 8todaytoday		#81,678Gemini 4 Argon	#21,788best of the pickedGPT-6 Astra	#191,619DeepSeek V4.1 Flash
SWE-bench VerifiedResolved · staletodaytoday	Oct 8todaytoday		#275.8%best of the pickedGemini 3 Flash	#672.8%GPT-5.2	#1170.0%DeepSeek-V3.2
SWE-Bench ProResolvedtodaytoday	Oct 8todaytoday		#958.8%Gemini 3.8 Flash	#390.2%best of the pickedGPT-6 Astra
Agents and tools3
BFCLOverall accuracytodaytoday	Oct 8todaytoday		#372.5%best of the pickedGemini 3 Pro	#763.0%o3	#1256.7%DeepSeek-V3.2
Search ArenaArena ratingtodaytoday	Oct 8todaytoday		#91,210Gemini 3.1 Pro Grounding	#11,257best of the pickedGPT-5.6 Sol
MCP AtlasPass ratetodaytoday	Oct 8todaytoday		#683.6%best of the pickedGemini 3.5 Flash	#1181.8%GPT-5.6
Vision2
Vision ArenaArena ratingtodaytoday	Oct 8todaytoday		#51,296best of the pickedGemini 3.7 Flash	#81,291GPT-6.1 Sol
Document ArenaArena ratingtodaytoday	Oct 8todaytoday		#161,463Gemini 3.5 Flash	#61,486best of the pickedGPT-5.5
Image2
Text-to-ImageArena ratingtodaytoday	Oct 8todaytoday		#61,328Gemini Nano Banana 2.1	#11,425best of the pickedGPT Image 2.5 Sunburst
Image EditArena ratingtodaytoday	Oct 8todaytoday		#61,428Gemini Nano Banana 2.1	#11,524best of the pickedGPT Image 2.5 Sunburst
Video2
Text-to-VideoArena ratingtodaytoday	Oct 8todaytoday		#11,516best of the pickedGemini Omni 1.1 Flash	#111,368Sora 2 Pro
Image-to-VideoArena ratingtodaytoday	Oct 8todaytoday		#21,488Gemini Omni 1.1 Flash
Speech2
Open ASRAverage WERtodaytoday	Oct 8todaytoday	#174.47 WERbest of the pickedARK-ASR-3B (Edge0)	#589.51 WERgemma-4-E4B-it (google)	#204.57 WERgpt-transcribe (openai)
Speech ArenaArena ratingtodaytoday	Oct 8todaytoday		#51,276best of the pickedGemini 3.8 Flash TTS	#351,102TTS 1 Hd
Embeddings1
MTEBMean task scoretodaytoday	Oct 8todaytoday		#568.4%gemini-embedding-001 (google)
Speed1
AA SpeedOutput speedtodaytoday	Oct 8todaytoday		#8125 tok/sGemini 3.8 Flash	#7128 tok/sGPT-6 Luna	#3223 tok/sbest of the pickedDeepSeek V4.1 Flash
Price1
AA PriceBlended pricetodaytoday	Oct 8todaytoday		#12$1.50Gemini 3.8 Flash	#2$0.20best of the pickedGPT-6 Luna	#7$0.53DeepSeek V4.1 Flash
Usage1
OpenRouterWeekly tokenstodaytoday	Oct 8todaytoday		#122.1T tokGemini 3.8 Flash	#66.5T tokGPT-6 Luna	#133.6T 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.