Translate
Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LiveBench 2.0 LMArena models.dev OpenRouter AIHOT cross-check
Back to leaderboard
Meta · Active

Muse Wonder

muse family · launched 2026-10-12

MultimodalReasoningToolsStructured
AITopic score67.3#33 overall

Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...

Evidence coverage95%5 evaluations · 2 institutions
Context / maximum output1M / 943.7ktokens
Cache / input / output$0.2 · $4 · $20USD per million tokens
Value / freshness48.0 / 100relative value · release freshness
Product profile

What this model supports

Inputtext, image, video, pdf, audio
Outputtext
Knowledge cutoffNot disclosed
WeightsProprietary / hosted
Capability profile

Strengths by domain

Coding65.81 public results
Research & reasoning67.81 public results
Professional work70.41 public results
Knowledge & instruction65.41 public results
Behind the score

Every result has a source

Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.

Coding1 results

AIHOT · CodingAIHOT65.80 scoreReading 65.8

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: AIHOT aggregateOpen evidence

Research & reasoning1 results

AIHOT · ResearchAIHOT67.80 scoreReading 67.8

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: AIHOT aggregateOpen evidence

Professional work1 results

AIHOT · ProfessionalAIHOT70.40 scoreReading 70.4

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: AIHOT aggregateOpen evidence

Knowledge & instruction1 results

AIHOT · KnowledgeAIHOT65.40 scoreReading 65.4

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: AIHOT aggregateOpen evidence

Human preference & indices3 results

AA IndexArtificial Analysis69.61 indexReading 72.3

Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: AIHOT aggregateOpen evidence
AIHOT aggregate leaderboardAIHOT67.30 scoreReading 67.3

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: AIHOT aggregateOpen evidence
Arena TextLMArena1,499.2 EloReading 67.3

Direct LMArena text leaderboard result.

Open evidence
Same builder

More from Meta