Every AI leaderboard

28 leaderboards · 992 models ranked

Abr Ai vs Meta vs Microsoft vs OpenAI

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.

  • Abr Ai
  • Meta
  • Microsoft
  • OpenAI

Head to head on 25 boards: OpenAI places best on 18, Meta places best on 6, Microsoft places best on 2 and Abr Ai places best on 0 (a tie counts for each). All 4 ranked on 1 of 27 boards.

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

BoardAbr AiMetaMicrosoftOpenAI
Chat2
MultiChallengeScoreyesterday#375.5%Muse Spark#182.0%best of the pickedGPT-6.1 Sol
Text ArenaArena ratingyesterday#31,511best of the pickedMuse Wonder#191,485GPT-5.6 Sol
Reasoning7
MMLU-ProAccuracy · staleyesterday#4782.8%Llama4 Behemoth#7576.0%Phi 4 Plus#389.3%best of the pickedo1
HLEAccuracyyesterday#740.6%Muse Spark#154.8%best of the pickedGPT-6 Astra
ARC-AGI-2Scoreyesterday#4157.5%Muse Spark Open#195.0%best of the pickedGPT-6 Astra
Epoch ECIECIyesterday#15162.0Muse Wonder#2169.2best of the pickedGPT-6 Astra
GPQA DiamondAccuracyyesterday#4989.8%Muse Spark#395.8%best of the pickedGPT-6 Astra
AA IntelligenceIndexyesterday#950.1Muse Wonder Full#456.9best of the pickedGPT-6 Astra
LiveBenchGlobal averageyesterday#681.6%Muse Spark 1.3#482.2%best of the pickedGPT-6 Astra
Coding4
Aider PolyglotPass rate · staleyesterday#4315.6%Llama 4 Maverick Instruct#188.0%best of the pickedGPT-5
SWE-Bench ProResolvedyesterday#490.2%best of the pickedMuse Wonder 1.0 Max Effort#490.2%best of the pickedGPT-6 Astra
WebDev ArenaArena ratingyesterday#81,723Muse Wonder Full#51,764best of the pickedGPT-6 Astra
SWE-bench VerifiedResolved · staleyesterday#3621.0%Llama 4 Maverick Instruct#672.8%best of the pickedGPT-5.2
Agents and tools3
BFCLOverall accuracy · staleyesterday#3637.3%Llama 4 Maverick 17b 128e#5028.8%Phi 4#763.0%best of the pickedo3
MCP AtlasPass rateyesterday#288.1%best of the pickedMuse Spark 1.1#1481.8%GPT-5.6
Search ArenaArena ratingyesterday#11,255GPT-5.6 Sol
Vision2
Document ArenaArena ratingyesterday#91,480Muse Spark 1.1#51,486best of the pickedGPT-5.6 Sol
Vision ArenaArena ratingyesterday#61,294best of the pickedMuse Spark#101,293GPT-6.1 Sol
Image2
Text-to-ImageArena ratingyesterday#111,266Muse Image#61,329MAI Image 2.6#11,429best of the pickedGPT Image 2.5 Sunburst
Image EditArena ratingyesterday#121,400Muse Image#41,468MAI Image 2.7#11,520best of the pickedGPT Image 2.5 Sunburst
Video1
Text-to-VideoArena ratingyesterday#101,457best of the pickedMuse Video#131,367Sora 2 Pro
Speech2
Open ASRAverage WERyesterday#5510.90 WERniagara-84m-batch.en (abr-ai)#307.00 WERmuse-voice-transcribe (meta)#35.55 WERbest of the pickedazure-speech-09-2026 (microsoft)#196.80 WERgpt-transcribe (openai)
Speech ArenaArena ratingyesterday#99846Metavoice V1#311,145best of the pickedAzure Hd 2.5#411,106TTS 1 Hd
Embeddings1
MTEBMean task scoreyesterday#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedyesterday#2513 tok/sMuse Wonder#1623 tok/sbest of the pickedGPT-6 Astra
Price1
AA PriceBlended priceyesterday#1$0.20best of the pickedMuse Ember#7$2.00GPT-6.1 Terra
Usage1
OpenRouterWeekly tokensyesterday#152.9T tokMuse Spark 1.3 Contributor#47.0T tokbest of the pickedGPT-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.

More comparisons