Advertise here
#38

Muse Wonder

Meta Release: 2026-10-13 Tested on: 2026-10-13 00:21 meta/muse-wonder::low
~1T total (~50B active)MoEClosedEstimated
(max) (xhigh) (high) (medium) (low) (minimal)

Summary

Muse Wonder scores 9.1 on AI BENCHY and ranks #38. It has 9.7 reliability, a 76.8% pass rate, $2.637 total cost, and 16.00s average response time.

What makes Muse Wonder unique: It stands out most in Domain specific, where it ranks #4, while Puzzle Solving is its weakest area at #16.

Model facts

Researched on 2026-10-13

Estimated
Parameters
~1T total (~50B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Meta does not disclose parameter counts or dense-versus-MoE architecture for this exact checkpoint. The 1T total / 50B active MoE values are a provisional, low-confidence catalog estimate carried from the Muse Spark family; they are not vendor-reported or measured Muse Wonder specifications. Available through Meta Model API and OpenRouter with no official public weights or checkpoint license. Wonder Full is a separate subscription-only model, not the max effort of this API checkpoint. Supports minimal, low, medium, high, xhigh and max reasoning; none is explicitly unsupported. Meta keeps raw reasoning private; OpenRouter returns reasoning summaries and provider-reported reasoning-token usage.

Parameter source 1 Parameter source 2 Availability source

Score

9.1

Consistency

9.6

Reliability

9.7

Total Cost (Current Price)

$2.637

Total Output Tokens

82,847

Total Input Tokens

244,997

Input Price

$4.000 / 1M

Output Price

$20.000 / 1M

Cache Read Price

$0.200 / 1M

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 6

Attempt pass rate: 76.8%

Flaky tests

1

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

16.00s

Response Time (max): 83.98s

Response Time (total): 367.91s

Wrong answer: 4 API error: 2

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#38 Muse Wonder

low
Cost
$0.080
Time
28.1s
Tokens
4,067 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Muse WonderlowvsMuse Spark 1.3highMuse WonderlowvsParetodefaultMuse WonderlowvsClaude Haiku 5.5xhighMuse WonderlowvsSeed 2.1 TurbohighMuse WonderlowvsGPT-5.3-CodexmediumMuse WonderlowvsMuse WonderminimalMuse WonderlowvsQwen3.8 Max (0902)highMuse WonderlowvsGemini 3.5 FlashlowMuse WonderlowvsQwen3.8 MAXmediumMuse WonderlowvsQwen3.8 Max (0902)medium

Category Breakdown

Category Score Consistency Tests Correct
Agentic 10.0 10.0
Anti-AI Tricks 10.0 10.0
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 10.0 10.0
Instructions following 6.5 10.0
Puzzle Solving 5.9 7.2
Tool Calling 9.8 10.0
Trivia 3.0 10.0

Compared models