Every AI leaderboard, side by side

Leaderboards28Models ranked835

China Mobile vs OpenAI vs Meta vs Microsoft

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.

  • China Mobile
  • OpenAI
  • Meta
  • Microsoft

Head to head on 24 boards: OpenAI places best on 16, Meta places best on 6, Microsoft places best on 2 and China Mobile places best on 0. All 4 ranked on 0 of 27 boards.

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

BoardChina MobileOpenAIMetaMicrosoft
Chat2
MultiChallengeScoreyesterday#469.2%GPT-5.4 Pro#175.5%best of the pickedMuse Spark
Text ArenaArena ratingyesterday#171,484GPT-5.6 Sol#81,494best of the pickedMuse Spark 1.3
Reasoning7
MMLU-ProAccuracy · staleyesterday#389.3%best of the pickedo1#4782.8%Llama4 Behemoth#7576.0%Phi 4 Plus
AA IntelligenceIndexyesterday#2433.9JT-4.1 Flash 236B A21B#452.7best of the pickedGPT-6 Astra#748.1Muse Spark 1.3
HLEAccuracyyesterday#154.8%best of the pickedGPT-6 Astra#640.6%Muse Spark
GPQA DiamondAccuracyyesterday#195.8%best of the pickedGPT-6 Astra#4189.8%Muse Spark
ARC-AGI-2Scoreyesterday#195.0%best of the pickedGPT-6 Astra#750.0%Llama 4 Maverick Instruct
Epoch ECIECIyesterday#2166.4best of the pickedGPT-6 Astra#19156.8Muse Spark 1.3
LiveBenchGlobal averageyesterday#482.2%best of the pickedGPT-6 Astra#681.6%Muse Spark 1.3
Coding4
Aider PolyglotPass rate · staleyesterday#188.0%best of the pickedGPT-5#4315.6%Llama 4 Maverick Instruct
WebDev ArenaArena ratingyesterday#21,788best of the pickedGPT-6 Astra#111,657Muse Spark 1.3
SWE-bench VerifiedResolved · staleyesterday#672.8%best of the pickedGPT-5.2#3621.0%Llama 4 Maverick Instruct
SWE-Bench ProResolvedyesterday#390.2%GPT-6 Astra
Agents and tools3
BFCLOverall accuracyyesterday#763.0%best of the pickedo3#3637.3%Llama 4 Maverick 17b 128e#5028.8%Phi 4
MCP AtlasPass rateyesterday#1181.8%GPT-5.6#188.1%best of the pickedMuse Spark 1.1
Search ArenaArena ratingyesterday#11,257GPT-5.6 Sol
Vision2
Vision ArenaArena ratingyesterday#81,291GPT-6.1 Sol#61,294best of the pickedMuse Spark
Document ArenaArena ratingyesterday#61,486best of the pickedGPT-5.5#121,471Muse Spark 1.3
Image2
Text-to-ImageArena ratingyesterday#11,425best of the pickedGPT Image 2.5 Sunburst#71,274Muse Image#51,333MAI Image 2.6
Image EditArena ratingyesterday#11,524best of the pickedGPT Image 2.5 Sunburst#61,403Muse Image#51,427MAI Image 2.6
Video1
Text-to-VideoArena ratingyesterday#111,368Sora 2 Pro#91,456best of the pickedMuse Video
Speech2
Open ASRAverage WERyesterday#204.57 WERgpt-transcribe (openai)#294.84 WERmuse-voice-transcribe (meta)#23.81 WERbest of the pickedazure-speech-07-2026 (microsoft)
Speech ArenaArena ratingyesterday#361,103TTS 1 Hd#92850Metavoice V1#281,131best of the pickedAzure Hd 2.5
Embeddings1
MTEBMean task scoreyesterday#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedyesterday#6138 tok/sGPT-6 Luna#4152 tok/sbest of the pickedMuse Spark 1.3
Price1
AA PriceBlended priceyesterday#2$0.20best of the pickedGPT-6 Luna#12$2.00Muse Spark 1.3
Usage1
OpenRouterWeekly tokensyesterday#66.2T tokbest of the pickedGPT-6 Luna#161.4T 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