Skip to content

OpenAI vs Meta vs Google vs Anthropic

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.

  • OpenAI
  • Meta
  • Google
  • Anthropic

Head to head on 26 boards: OpenAI places best on 10, Anthropic places best on 9, Google places best on 4 and Meta places best on 3. All 4 ranked on 19 of 28 boards.

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

BoardOpenAIMetaGoogleAnthropic
Chat2
Text ArenaArena ratingtoday#161,483GPT-5.6 Sol#61,496Muse Spark 1.2#81,492Gemini 3.8 Flash#11,509best of the pickedClaude Opus 5.5
MultiChallengeScoretoday#469.2%GPT-5.4 Pro#175.5%best of the pickedMuse Spark#371.4%Gemini 3.1 Pro Preview#1259.0%Claude Opus 4.5
Reasoning7
AA IntelligenceIndextoday#352.7GPT-6 Astra#448.1Muse Spark 1.3#1540.9Gemini 3.8 Flash#157.6best of the pickedClaude Opus 5.5
HLEAccuracytoday#154.8%best of the pickedGPT-6 Astra#640.6%Muse Spark#346.4%Gemini 3.1 Pro Preview#246.5%Claude Fable 5.1
GPQA DiamondAccuracytoday#195.8%best of the pickedGPT-6 Astra#3589.8%Muse Spark#295.4%Gemini 3.8 Flash#1093.9%Claude Opus 5
Epoch ECIECItoday#1166.6best of the pickedGPT-6 Astra#15156.9Muse Spark 1.3#11157.7Gemini 3.7 Flash#2165.0Claude Fable 5.1
ARC-AGI-2Scoretoday#195.0%best of the pickedGPT-6 Astra#710.0%Llama 4 Maverick Instruct#689.2%Gemini 3.8 Flash#293.3%Claude Opus 5.5
LiveBenchGlobal averagetoday#482.2%GPT-6 Astra#581.6%Muse Spark 1.3#1378.8%Gemini 3.7 Flash#183.4%best of the pickedClaude Fable 5.1
MMLU-ProAccuracy · staletoday#389.3%o1#4782.8%Llama4 Behemoth#191.2%best of the pickedGemini 3.1 Pro Preview#489.1%Claude Opus 4.6
Coding4
WebDev ArenaArena ratingtoday#21,792GPT-6 Astra#81,656Muse Spark 1.3#201,593Gemini 3.7 Flash#11,827best of the pickedClaude Opus 5.5
SWE-bench VerifiedResolved · staletoday#672.8%GPT-5.2#3621.0%Llama 4 Maverick Instruct#275.8%Gemini 3 Flash#176.8%best of the pickedClaude Opus 4.5
Aider PolyglotPass rate · staletoday#188.0%best of the pickedGPT-5#4315.6%Llama 4 Maverick Instruct#383.1%Gemini 2.5 Pro (Jun 2025)#1072.0%Claude Opus 4
SWE-Bench ProResolvedtoday#390.2%GPT-6 Astra#958.8%Gemini 3.8 Flash#198.0%best of the pickedClaude Opus 5
Agents and tools3
BFCLOverall accuracytoday#763.0%o3#3637.3%Llama 4 Maverick 17b 128e#372.5%Gemini 3 Pro#177.5%best of the pickedClaude Opus 4.5
MCP AtlasPass ratetoday#1181.8%GPT-5.6#188.1%best of the pickedMuse Spark 1.1#683.6%Gemini 3.5 Flash#287.2%Claude Fable 5.1
Search ArenaArena ratingtoday#11,257best of the pickedGPT-5.6 Sol#91,210Gemini 3.1 Pro Grounding#21,253Claude Opus 4.6
Vision2
Vision ArenaArena ratingtoday#111,287GPT-5.5#51,294Muse Spark 1.3#101,289Gemini 3 Pro#11,310best of the pickedClaude Fable 5
Document ArenaArena ratingtoday#61,486GPT-5.5#121,471Muse Spark 1.3#161,463Gemini 3.5 Flash#11,516best of the pickedClaude Opus 5
Image2
Text-to-ImageArena ratingtoday#11,424best of the pickedGPT Image 2.5 Sunburst#71,276Muse Image#91,261Gemini 3.1 Flash Image
Image EditArena ratingtoday#11,526best of the pickedGPT Image 2.5 Sunburst#61,402Muse Image#91,390Gemini 3 Pro Image
Video2
Text-to-VideoArena ratingtoday#111,368Sora 2 Pro#91,456Muse Video#11,516best of the pickedGemini Omni 1.1 Flash
Image-to-VideoArena ratingtoday#21,488Gemini Omni 1.1 Flash
Speech2
Speech ArenaArena ratingtoday#321,104TTS 1 Hd#89847Metavoice V1#21,268best of the pickedGemini 3.8 Flash TTS
Open ASRAverage WERtoday#535.78 WERwhisper-large-v3 (openai)#284.84 WERbest of the pickedmuse-voice-transcribe (meta)#669.51 WERgemma-4-E4B-it (google)
Embeddings1
MTEBMean task scoretoday#568.4%gemini-embedding-001 (google)
Speed1
AA SpeedOutput speedtoday#5154 tok/sGPT-6 Luna#2232 tok/sMuse Spark 1.3#1308 tok/sbest of the pickedGemini 3.8 Flash#988 tok/sClaude Opus 5.5
Price1
AA PriceBlended pricetoday#1$0.20best of the pickedGPT-6 Luna#11$2.00Muse Spark 1.3#9$1.50Gemini 3.8 Flash#17$4.00Claude Sonnet 5
Usage1
OpenRouterWeekly tokenstoday#58.6T tokbest of the pickedGPT-5.6 Luna#151.8T tokMuse Spark 1.3 Contributor#142.2T tokGemini 3.8 Flash#191.5T tokClaude Sonnet 5

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.