Skip to content

Maya Research vs OpenAI vs Anthropic 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.

  • Maya Research
  • OpenAI
  • Anthropic
  • Meta

Head to head on 26 boards: OpenAI places best on 12, Anthropic places best on 9, Meta places best on 5 and Maya Research places best on 0. All 4 ranked on 0 of 26 boards.

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

BoardMaya ResearchOpenAIAnthropicMeta
Chat2
Text ArenaArena ratingtoday#161,483GPT-5.6 Sol#11,509best of the pickedClaude Opus 5.5#61,496Muse Spark 1.2
MultiChallengeScoretoday#469.2%GPT-5.4 Pro#1259.0%Claude Opus 4.5#175.5%best of the pickedMuse Spark
Reasoning7
AA IntelligenceIndextoday#352.7GPT-6 Astra#157.6best of the pickedClaude Opus 5.5#448.1Muse Spark 1.3
HLEAccuracytoday#154.8%best of the pickedGPT-6 Astra#246.5%Claude Fable 5.1#640.6%Muse Spark
GPQA DiamondAccuracytoday#195.8%best of the pickedGPT-6 Astra#1093.9%Claude Opus 5#3589.8%Muse Spark
Epoch ECIECItoday#1166.6best of the pickedGPT-6 Astra#2165.0Claude Fable 5.1#15156.9Muse Spark 1.3
ARC-AGI-2Scoretoday#195.0%best of the pickedGPT-6 Astra#293.3%Claude Opus 5.5#710.0%Llama 4 Maverick Instruct
LiveBenchGlobal averagetoday#482.2%GPT-6 Astra#183.4%best of the pickedClaude Fable 5.1#581.6%Muse Spark 1.3
MMLU-ProAccuracy · staletoday#389.3%best of the pickedo1#489.1%Claude Opus 4.6#4782.8%Llama4 Behemoth
Coding4
WebDev ArenaArena ratingtoday#21,792GPT-6 Astra#11,827best of the pickedClaude Opus 5.5#81,656Muse Spark 1.3
SWE-bench VerifiedResolved · staletoday#672.8%GPT-5.2#176.8%best of the pickedClaude Opus 4.5#3621.0%Llama 4 Maverick Instruct
Aider PolyglotPass rate · staletoday#188.0%best of the pickedGPT-5#1072.0%Claude Opus 4#4315.6%Llama 4 Maverick Instruct
SWE-Bench ProResolvedtoday#390.2%GPT-6 Astra#198.0%best of the pickedClaude Opus 5
Agents and tools3
BFCLOverall accuracytoday#763.0%o3#177.5%best of the pickedClaude Opus 4.5#3637.3%Llama 4 Maverick 17b 128e
MCP AtlasPass ratetoday#1181.8%GPT-5.6#287.2%Claude Fable 5.1#188.1%best of the pickedMuse Spark 1.1
Search ArenaArena ratingtoday#11,257best of the pickedGPT-5.6 Sol#21,253Claude Opus 4.6
Vision2
Vision ArenaArena ratingtoday#111,287GPT-5.5#11,310best of the pickedClaude Fable 5#51,294Muse Spark 1.3
Document ArenaArena ratingtoday#61,486GPT-5.5#11,516best of the pickedClaude Opus 5#121,471Muse Spark 1.3
Image2
Text-to-ImageArena ratingtoday#11,424best of the pickedGPT Image 2.5 Sunburst#71,276Muse Image
Image EditArena ratingtoday#11,526best of the pickedGPT Image 2.5 Sunburst#61,402Muse Image
Video1
Text-to-VideoArena ratingtoday#111,368Sora 2 Pro#91,456best of the pickedMuse Video
Speech2
Speech ArenaArena ratingtoday#471,071Maya 2 Flash#321,104best of the pickedTTS 1 Hd#89847Metavoice V1
Open ASRAverage WERtoday#535.78 WERwhisper-large-v3 (openai)#284.84 WERbest of the pickedmuse-voice-transcribe (meta)
Speed1
AA SpeedOutput speedtoday#5154 tok/sGPT-6 Luna#988 tok/sClaude Opus 5.5#2232 tok/sbest of the pickedMuse Spark 1.3
Price1
AA PriceBlended pricetoday#1$0.20best of the pickedGPT-6 Luna#17$4.00Claude Sonnet 5#11$2.00Muse Spark 1.3
Usage1
OpenRouterWeekly tokenstoday#58.6T tokbest of the pickedGPT-5.6 Luna#191.5T tokClaude Sonnet 5#151.8T 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

New #1s by email

Saturdays, only in weeks when a leaderboard has a new #1.

Double opt-in. Unsubscribe any time.