Every AI leaderboard

28 leaderboards · 915 models ranked

Krea vs Meta vs DeepSeek 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.

  • Krea
  • Meta
  • DeepSeek
  • Anthropic

Head to head on 22 boards: Anthropic places best on 16, Meta places best on 3, DeepSeek places best on 2 and Krea places best on 1. All 4 ranked on 0 of 26 boards.

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

BoardKreaMetaDeepSeekAnthropic
Chat2
Text ArenaArena ratingyesterday#31,509Muse Wonder#291,476DeepSeek V4.1 Flash#21,509best of the pickedClaude Opus 5.5
MultiChallengeScoreyesterday#375.5%best of the pickedMuse Spark#2846.1%DeepSeek V3P1#867.7%Claude Haiku 5.5
Reasoning7
AA IntelligenceIndexyesterday#355.8Muse Wonder Full#1445.1DeepSeek V4.1 Flash#157.6best of the pickedClaude Opus 5.5
Epoch ECIECIyesterday#12161.8Muse Wonder#32155.9DeepSeek V4.1 Flash#1168.8best of the pickedClaude Opus 5.5
LiveBenchGlobal averageyesterday#681.6%Muse Spark 1.3#881.1%DeepSeek V4.1 Flash#183.4%best of the pickedClaude Fable 5.1
GPQA DiamondAccuracyyesterday#4389.8%Muse Spark#1993.2%DeepSeek V4.1 Flash#395.6%best of the pickedClaude Sonnet 5.5
ARC-AGI-2Scoreyesterday#3857.5%Muse Spark Open#1878.1%DeepSeek V4.1 Flash#393.3%best of the pickedClaude Opus 5.5
MMLU-ProAccuracy · staleyesterday#4782.8%Llama4 Behemoth#3385.0%DeepSeek-V3.2#489.1%best of the pickedClaude Opus 4.6
HLEAccuracyyesterday#740.6%Muse Spark#246.5%best of the pickedClaude Fable 5.1
Coding4
WebDev ArenaArena ratingyesterday#61,726Muse Wonder Full#121,665DeepSeek V4.1 Flash#11,807best of the pickedClaude Opus 5.5
SWE-bench VerifiedResolved · staleyesterday#3621.0%Llama 4 Maverick Instruct#1170.0%DeepSeek-V3.2#176.8%best of the pickedClaude Opus 4.5
Aider PolyglotPass rate · staleyesterday#4315.6%Llama 4 Maverick Instruct#874.2%best of the pickedDeepSeek-V3.2#1072.0%Claude Opus 4
SWE-Bench ProResolvedyesterday#490.2%Muse Wonder 1.0 Max Effort#198.0%best of the pickedClaude Opus 5
Agents and tools3
BFCLOverall accuracy · staleyesterday#3637.3%Llama 4 Maverick 17b 128e#1256.7%DeepSeek-V3.2#177.5%best of the pickedClaude Opus 4.5
MCP AtlasPass rateyesterday#188.1%best of the pickedMuse Spark 1.1#287.2%Claude Fable 5.1
Search ArenaArena ratingyesterday#41,233Claude Fable 5.1
Vision2
Vision ArenaArena ratingyesterday#61,294Muse Spark#391,261DeepSeek V4.1 Flash#11,309best of the pickedClaude Fable 5
Document ArenaArena ratingyesterday#91,479Muse Spark 1.1#11,499best of the pickedClaude Fable 5
Image2
Image EditArena ratingyesterday#71,411best of the pickedKrea 3 Ultra#91,398Muse Image
Text-to-ImageArena ratingyesterday#411,124Krea 2#81,274best of the pickedMuse Image
Video1
Text-to-VideoArena ratingyesterday#91,456Muse Video
Speech2
Open ASRAverage WERyesterday#326.30 WERmuse-voice-transcribe (meta)
Speech ArenaArena ratingyesterday#95846Metavoice V1
Speed1
AA SpeedOutput speedyesterday#6195 tok/sMuse Wonder#8181 tok/sDeepSeek V4 Flash Vision#3234 tok/sbest of the pickedClaude Haiku 5.5
Price1
AA PriceBlended priceyesterday#17$2.00Muse Spark Open#9$0.53DeepSeek V4.1 Flash#3$0.20best of the pickedClaude Haiku 5.5
Usage1
OpenRouterWeekly tokensyesterday#152.8T tokMuse Spark 1.3 Contributor#133.6T tokbest of the pickedDeepSeek V4.1 Flash#68.3T 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