Skip to content

Compare models

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.

Meta is ranked on 24 boards. Add another to compare.

BoardMeta
Chat2
MultiChallengeScoretoday#175.5%Muse Spark
Text ArenaArena ratingtoday#61,496Muse Spark 1.2
Reasoning7
AA IntelligenceIndextoday#448.1Muse Spark 1.3
LiveBenchGlobal averagetoday#581.6%Muse Spark 1.3
HLEAccuracytoday#640.6%Muse Spark
Epoch ECIECItoday#15156.9Muse Spark 1.3
GPQA DiamondAccuracytoday#3589.8%Muse Spark
MMLU-ProAccuracy · staletoday#4782.8%Llama4 Behemoth
ARC-AGI-2Scoretoday#710.0%Llama 4 Maverick Instruct
Coding3
WebDev ArenaArena ratingtoday#81,656Muse Spark 1.3
SWE-bench VerifiedResolved · staletoday#3621.0%Llama 4 Maverick Instruct
Aider PolyglotPass rate · staletoday#4315.6%Llama 4 Maverick Instruct
Agents and tools2
MCP AtlasPass ratetoday#188.1%Muse Spark 1.1
BFCLOverall accuracytoday#3637.3%Llama 4 Maverick 17b 128e
Vision2
Vision ArenaArena ratingtoday#51,294Muse Spark 1.3
Document ArenaArena ratingtoday#121,471Muse Spark 1.3
Image2
Image EditArena ratingtoday#61,402Muse Image
Text-to-ImageArena ratingtoday#71,276Muse Image
Video1
Text-to-VideoArena ratingtoday#91,456Muse Video
Speech2
Open ASRAverage WERtoday#284.84 WERmuse-voice-transcribe (meta)
Speech ArenaArena ratingtoday#89847Metavoice V1
Speed1
AA SpeedOutput speedtoday#2232 tok/sMuse Spark 1.3
Price1
AA PriceBlended pricetoday#11$2.00Muse Spark 1.3
Usage1
OpenRouterWeekly tokenstoday#151.8T 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.

Ready-made comparisons

New #1s by email

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

Double opt-in. Unsubscribe any time.