Skip to content

China Mobile vs Anthropic 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
  • Anthropic
  • Microsoft

Head to head on 3 boards: Anthropic places best on 3, China Mobile places best on 0 and Microsoft places best on 0. All 3 ranked on 0 of 26 boards.

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

BoardChina MobileAnthropicMicrosoft
Chat2
Text ArenaArena ratingtoday#21,505Claude Opus 4.6
MultiChallengeScoretoday#1259.0%Claude Opus 4.5
Reasoning7
AA IntelligenceIndextoday#2433.9JT-4.1 Flash 236B A21B#157.6best of the pickedClaude Opus 5.5
MMLU-ProAccuracy · staletoday#489.1%best of the pickedClaude Opus 4.6#7576.0%Phi 4 Plus
Epoch ECIECItoday#1167.3Claude Opus 5.5
LiveBenchGlobal averagetoday#183.4%Claude Fable 5.1
HLEAccuracytoday#246.5%Claude Fable 5.1
GPQA DiamondAccuracytoday#295.6%Claude Sonnet 5.5
ARC-AGI-2Scoretoday#393.3%Claude Opus 5.5
Coding4
WebDev ArenaArena ratingtoday#11,815Claude Opus 5.5
SWE-Bench ProResolvedtoday#198.0%Claude Opus 5
SWE-bench VerifiedResolved · staletoday#176.8%Claude Opus 4.5
Aider PolyglotPass rate · staletoday#1072.0%Claude Opus 4
Agents and tools3
BFCLOverall accuracytoday#177.5%best of the pickedClaude Opus 4.5#5028.8%Phi 4
MCP AtlasPass ratetoday#287.2%Claude Fable 5.1
Search ArenaArena ratingtoday#21,253Claude Opus 4.6
Vision2
Vision ArenaArena ratingtoday#11,309Claude Fable 5
Document ArenaArena ratingtoday#11,516Claude Opus 5
Image2
Text-to-ImageArena ratingtoday#41,335MAI Image 2.6
Image EditArena ratingtoday#51,427MAI Image 2.6
Speech2
Open ASRAverage WERtoday#23.81 WERazure-speech-07-2026 (microsoft)
Speech ArenaArena ratingtoday#271,131Azure Hd 2.5
Embeddings1
MTEBMean task scoretoday#174.3%harrier-oss-v1-27b (microsoft)
Speed1
AA SpeedOutput speedtoday#5139 tok/sClaude Sonnet 5.5
Price1
AA PriceBlended pricetoday#17$4.00Claude Sonnet 5.5
Usage1
OpenRouterWeekly tokenstoday#122.5T tokClaude 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.

More comparisons

New #1s by email

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

Double opt-in. Unsubscribe any time.