China Mobile vs Meta vs Anthropic

• CMChina Mobile
• Meta
• Anthropic

Add a lab

Add:OpenAIGoogleMicrosoftXiaomi

Head to head on 19 boards: Anthropic places best on 15, Meta places best on 4 and China Mobile places best on 0. All 3 ranked on 1 of 26 boards.

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

CMChina MobileMetaAnthropic

Board	Read	CMChina Mobile	Meta	Anthropic
Chat2
MultiChallengeScoretodaytoday	Oct 5todaytoday		#175.5%best of the pickedMuse Spark	#1259.0%Claude Opus 4.5
Text ArenaArena ratingtodaytoday	Oct 5todaytoday		#81,494Muse Spark 1.3	#21,505best of the pickedClaude Opus 4.6
Reasoning7
AA IntelligenceIndextodaytoday	Oct 5todaytoday	#2433.9JT-4.1 Flash 236B A21B	#748.1Muse Spark 1.3	#157.6best of the pickedClaude Opus 5.5
Epoch ECIECItodaytoday	Oct 5todaytoday		#17156.9Muse Spark 1.3	#1167.3best of the pickedClaude Opus 5.5
LiveBenchGlobal averagetodaytoday	Oct 5todaytoday		#681.6%Muse Spark 1.3	#183.4%best of the pickedClaude Fable 5.1
HLEAccuracytodaytoday	Oct 5todaytoday		#640.6%Muse Spark	#246.5%best of the pickedClaude Fable 5.1
GPQA DiamondAccuracytodaytoday	Oct 5todaytoday		#4189.8%Muse Spark	#295.6%best of the pickedClaude Sonnet 5.5
ARC-AGI-2Scoretodaytoday	Oct 5todaytoday		#750.0%Llama 4 Maverick Instruct	#393.3%best of the pickedClaude Opus 5.5
MMLU-ProAccuracy · staletodaytoday	Oct 5todaytoday		#4782.8%Llama4 Behemoth	#489.1%best of the pickedClaude Opus 4.6
Coding4
WebDev ArenaArena ratingtodaytoday	Oct 5todaytoday		#111,657Muse Spark 1.3	#11,815best of the pickedClaude Opus 5.5
SWE-bench VerifiedResolved · staletodaytoday	Oct 5todaytoday		#3621.0%Llama 4 Maverick Instruct	#176.8%best of the pickedClaude Opus 4.5
Aider PolyglotPass rate · staletodaytoday	Oct 5todaytoday		#4315.6%Llama 4 Maverick Instruct	#1072.0%best of the pickedClaude Opus 4
SWE-Bench ProResolvedtodaytoday	Oct 5todaytoday			#198.0%Claude Opus 5
Agents and tools3
BFCLOverall accuracytodaytoday	Oct 5todaytoday		#3637.3%Llama 4 Maverick 17b 128e	#177.5%best of the pickedClaude Opus 4.5
MCP AtlasPass ratetodaytoday	Oct 5todaytoday		#188.1%best of the pickedMuse Spark 1.1	#287.2%Claude Fable 5.1
Search ArenaArena ratingtodaytoday	Oct 5todaytoday			#21,253Claude Opus 4.6
Vision2
Vision ArenaArena ratingtodaytoday	Oct 5todaytoday		#61,294Muse Spark	#11,309best of the pickedClaude Fable 5
Document ArenaArena ratingtodaytoday	Oct 5todaytoday		#121,471Muse Spark 1.3	#11,516best of the pickedClaude Opus 5
Image2
Image EditArena ratingtodaytoday	Oct 5todaytoday		#61,403Muse Image
Text-to-ImageArena ratingtodaytoday	Oct 5todaytoday		#71,276Muse Image
Video1
Text-to-VideoArena ratingtodaytoday	Oct 5todaytoday		#91,456Muse Video
Speech2
Open ASRAverage WERtodaytoday	Oct 5todaytoday		#284.84 WERmuse-voice-transcribe (meta)
Speech ArenaArena ratingtodaytoday	Oct 5todaytoday		#91850Metavoice V1
Speed1
AA SpeedOutput speedtodaytoday	Oct 5todaytoday		#4152 tok/sbest of the pickedMuse Spark 1.3	#5139 tok/sClaude Sonnet 5.5
Price1
AA PriceBlended pricetodaytoday	Oct 5todaytoday		#12$2.00best of the pickedMuse Spark 1.3	#17$4.00Claude Sonnet 5.5
Usage1
OpenRouterWeekly tokenstodaytoday	Oct 5todaytoday		#161.4T tokMuse Spark 1.3 Contributor	#122.5T tokbest of the pickedClaude Opus 5.5

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.