Every AI leaderboard

28 leaderboards · 915 models ranked

Krea vs OpenAI vs DeepSeek vs Meta

Each lab shows its best-ranked model on every board. One row per board where at least one is ranked, from each board's current capture.

  • Krea
  • OpenAI
  • DeepSeek
  • Meta

Head to head on 25 boards: OpenAI places best on 18, Meta places best on 7, DeepSeek places best on 1 and Krea places best on 0 (a tie counts for each). All 4 ranked on 0 of 26 boards.

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

BoardKreaOpenAIDeepSeekMeta
Chat2
MultiChallengeScoreyesterday#182.0%best of the pickedGPT-6.1 Sol#2846.1%DeepSeek V3P1#375.5%Muse Spark
Text ArenaArena ratingyesterday#181,485GPT-5.6 Sol#291,476DeepSeek V4.1 Flash#31,509best of the pickedMuse Wonder
Reasoning7
ARC-AGI-2Scoreyesterday#195.0%best of the pickedGPT-6 Astra#1878.1%DeepSeek V4.1 Flash#3857.5%Muse Spark Open
GPQA DiamondAccuracyyesterday#295.8%best of the pickedGPT-6 Astra#1993.2%DeepSeek V4.1 Flash#4389.8%Muse Spark
Epoch ECIECIyesterday#2168.8best of the pickedGPT-6 Astra#32155.9DeepSeek V4.1 Flash#12161.8Muse Wonder
AA IntelligenceIndexyesterday#652.7GPT-6 Astra#1445.1DeepSeek V4.1 Flash#355.8best of the pickedMuse Wonder Full
MMLU-ProAccuracy · staleyesterday#389.3%best of the pickedo1#3385.0%DeepSeek-V3.2#4782.8%Llama4 Behemoth
LiveBenchGlobal averageyesterday#482.2%best of the pickedGPT-6 Astra#881.1%DeepSeek V4.1 Flash#681.6%Muse Spark 1.3
HLEAccuracyyesterday#154.8%best of the pickedGPT-6 Astra#740.6%Muse Spark
Coding4
Aider PolyglotPass rate · staleyesterday#188.0%best of the pickedGPT-5#874.2%DeepSeek-V3.2#4315.6%Llama 4 Maverick Instruct
WebDev ArenaArena ratingyesterday#21,774best of the pickedGPT-6 Astra#121,665DeepSeek V4.1 Flash#61,726Muse Wonder Full
SWE-bench VerifiedResolved · staleyesterday#672.8%best of the pickedGPT-5.2#1170.0%DeepSeek-V3.2#3621.0%Llama 4 Maverick Instruct
SWE-Bench ProResolvedyesterday#490.2%best of the pickedGPT-6 Astra#490.2%best of the pickedMuse Wonder 1.0 Max Effort
Agents and tools3
BFCLOverall accuracy · staleyesterday#763.0%best of the pickedo3#1256.7%DeepSeek-V3.2#3637.3%Llama 4 Maverick 17b 128e
MCP AtlasPass rateyesterday#1181.8%GPT-5.6#188.1%best of the pickedMuse Spark 1.1
Search ArenaArena ratingyesterday#11,258GPT-5.6 Sol
Vision2
Vision ArenaArena ratingyesterday#71,294GPT-6.1 Sol#391,261DeepSeek V4.1 Flash#61,294best of the pickedMuse Spark
Document ArenaArena ratingyesterday#61,489best of the pickedGPT-5.6 Sol#91,479Muse Spark 1.1
Image2
Text-to-ImageArena ratingyesterday#411,124Krea 2#11,425best of the pickedGPT Image 2.5 Sunburst#81,274Muse Image
Image EditArena ratingyesterday#71,411Krea 3 Ultra#11,514best of the pickedGPT Image 2.5 Sunburst#91,398Muse Image
Video1
Text-to-VideoArena ratingyesterday#111,368Sora 2 Pro#91,456best of the pickedMuse Video
Speech2
Open ASRAverage WERyesterday#215.96 WERbest of the pickedgpt-transcribe (openai)#326.30 WERmuse-voice-transcribe (meta)
Speech ArenaArena ratingyesterday#391,105best of the pickedTTS 1 Hd#95846Metavoice V1
Speed1
AA SpeedOutput speedyesterday#12129 tok/sGPT-6 Luna#8181 tok/sDeepSeek V4 Flash Vision#6195 tok/sbest of the pickedMuse Wonder
Price1
AA PriceBlended priceyesterday#3$0.20best of the pickedGPT-6 Luna#9$0.53DeepSeek V4.1 Flash#17$2.00Muse Spark Open
Usage1
OpenRouterWeekly tokensyesterday#58.4T tokGPT-6 Luna#133.6T tokbest of the pickedDeepSeek V4.1 Flash#152.8T tokMuse Spark 1.3 Contributor

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.

More comparisons