Every AI leaderboard

28 leaderboards · 915 models ranked

Krea 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.

  • Krea
  • Meta

Head to head on 2 boards: Krea places best on 1 and Meta places best on 1. Both ranked on 2 of 25 boards.

BoardKreaMeta
Chat2
Text ArenaArena ratingyesterday#31,509Muse Wonder
MultiChallengeScoreyesterday#375.5%Muse Spark
Reasoning7
AA IntelligenceIndexyesterday#355.8Muse Wonder Full
LiveBenchGlobal averageyesterday#681.6%Muse Spark 1.3
HLEAccuracyyesterday#740.6%Muse Spark
Epoch ECIECIyesterday#12161.8Muse Wonder
ARC-AGI-2Scoreyesterday#3857.5%Muse Spark Open
GPQA DiamondAccuracyyesterday#4389.8%Muse Spark
MMLU-ProAccuracy · staleyesterday#4782.8%Llama4 Behemoth
Coding4
SWE-Bench ProResolvedyesterday#490.2%Muse Wonder 1.0 Max Effort
WebDev ArenaArena ratingyesterday#61,726Muse Wonder Full
SWE-bench VerifiedResolved · staleyesterday#3621.0%Llama 4 Maverick Instruct
Aider PolyglotPass rate · staleyesterday#4315.6%Llama 4 Maverick Instruct
Agents and tools2
MCP AtlasPass rateyesterday#188.1%Muse Spark 1.1
BFCLOverall accuracy · staleyesterday#3637.3%Llama 4 Maverick 17b 128e
Vision2
Vision ArenaArena ratingyesterday#61,294Muse Spark
Document ArenaArena ratingyesterday#91,479Muse Spark 1.1
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
Price1
AA PriceBlended priceyesterday#17$2.00Muse Spark Open
Usage1
OpenRouterWeekly tokensyesterday#152.8T 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