Every AI leaderboard

28 leaderboards · 915 models ranked

P99lab vs Meta vs OpenAI vs DeepSeek

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.

  • P99lab
  • Meta
  • OpenAI
  • DeepSeek

Head to head on 25 boards: OpenAI places best on 17, Meta places best on 7, P99lab places best on 1 and DeepSeek places best on 1 (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.

BoardP99labMetaOpenAIDeepSeek
Chat2
MultiChallengeScoreyesterday#375.5%Muse Spark#182.0%best of the pickedGPT-6.1 Sol#2846.1%DeepSeek V3P1
Text ArenaArena ratingyesterday#31,509best of the pickedMuse Wonder#181,485GPT-5.6 Sol#291,476DeepSeek V4.1 Flash
Reasoning7
ARC-AGI-2Scoreyesterday#3857.5%Muse Spark Open#195.0%best of the pickedGPT-6 Astra#1878.1%DeepSeek V4.1 Flash
GPQA DiamondAccuracyyesterday#4389.8%Muse Spark#295.8%best of the pickedGPT-6 Astra#1993.2%DeepSeek V4.1 Flash
Epoch ECIECIyesterday#12161.8Muse Wonder#2168.8best of the pickedGPT-6 Astra#32155.9DeepSeek V4.1 Flash
AA IntelligenceIndexyesterday#355.8best of the pickedMuse Wonder Full#652.7GPT-6 Astra#1445.1DeepSeek V4.1 Flash
MMLU-ProAccuracy · staleyesterday#4782.8%Llama4 Behemoth#389.3%best of the pickedo1#3385.0%DeepSeek-V3.2
LiveBenchGlobal averageyesterday#681.6%Muse Spark 1.3#482.2%best of the pickedGPT-6 Astra#881.1%DeepSeek V4.1 Flash
HLEAccuracyyesterday#740.6%Muse Spark#154.8%best of the pickedGPT-6 Astra
Coding4
Aider PolyglotPass rate · staleyesterday#4315.6%Llama 4 Maverick Instruct#188.0%best of the pickedGPT-5#874.2%DeepSeek-V3.2
WebDev ArenaArena ratingyesterday#61,726Muse Wonder Full#21,774best of the pickedGPT-6 Astra#121,665DeepSeek V4.1 Flash
SWE-bench VerifiedResolved · staleyesterday#3621.0%Llama 4 Maverick Instruct#672.8%best of the pickedGPT-5.2#1170.0%DeepSeek-V3.2
SWE-Bench ProResolvedyesterday#490.2%best of the pickedMuse Wonder 1.0 Max Effort#490.2%best of the pickedGPT-6 Astra
Agents and tools3
BFCLOverall accuracy · staleyesterday#3637.3%Llama 4 Maverick 17b 128e#763.0%best of the pickedo3#1256.7%DeepSeek-V3.2
MCP AtlasPass rateyesterday#188.1%best of the pickedMuse Spark 1.1#1181.8%GPT-5.6
Search ArenaArena ratingyesterday#11,258GPT-5.6 Sol
Vision2
Vision ArenaArena ratingyesterday#61,294best of the pickedMuse Spark#71,294GPT-6.1 Sol#391,261DeepSeek V4.1 Flash
Document ArenaArena ratingyesterday#91,479Muse Spark 1.1#61,489best of the pickedGPT-5.6 Sol
Image2
Text-to-ImageArena ratingyesterday#81,274Muse Image#11,425best of the pickedGPT Image 2.5 Sunburst
Image EditArena ratingyesterday#91,398Muse Image#11,514best of the pickedGPT Image 2.5 Sunburst
Video1
Text-to-VideoArena ratingyesterday#91,456best of the pickedMuse Video#111,368Sora 2 Pro
Speech2
Open ASRAverage WERyesterday#34.98 WERbest of the pickedaudrey-0.7 (p99lab)#326.30 WERmuse-voice-transcribe (meta)#215.96 WERgpt-transcribe (openai)
Speech ArenaArena ratingyesterday#95846Metavoice V1#391,105best of the pickedTTS 1 Hd
Speed1
AA SpeedOutput speedyesterday#6195 tok/sbest of the pickedMuse Wonder#12129 tok/sGPT-6 Luna#8181 tok/sDeepSeek V4 Flash Vision
Price1
AA PriceBlended priceyesterday#17$2.00Muse Spark Open#3$0.20best of the pickedGPT-6 Luna#9$0.53DeepSeek V4.1 Flash
Usage1
OpenRouterWeekly tokensyesterday#152.8T tokMuse Spark 1.3 Contributor#58.4T 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.

More comparisons