Advertise here
#30

Muse Spark Open

Meta Release: 2026-10-15 Tested on: 2026-10-16 00:21 meta/muse-spark-open::high
816B total (42B active)MoEWeights available
(xhigh) (high) (medium) (low)

Summary

Muse Spark Open scores 9.2 on AI BENCHY and ranks #30. It has 9.4 reliability, a 76.8% pass rate, $1.782 total cost, and 151.96s average response time.

Model facts

Researched on 2026-10-15

Reported
Parameters
816B total (42B active)
Architecture
MoE
Availability
Weights available
License
Muse Model License

Open weights under the custom Muse Model License, with attribution, usage-policy and Model-as-a-Service revenue terms. The official model metadata reports 816B total and 42B active parameters; its chat template declares low, medium, high and xhigh reasoning strengths.

Parameter source 1 Parameter source 2 Availability source

Score

9.2

Consistency

9.6

Reliability

9.4

Total Cost (Current Price)

$1.782

Total Output Tokens

339,545

Total Input Tokens

270,889

Input Price

$1.250 / 1M

Output Price

$4.250 / 1M

Cache Read Price

$0.150 / 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)

151.96s

Response Time (max): 960.01s

Response Time (total): 3495.01s

Timed out: 2 Wrong answer: 2 API error: 1 Did not follow instructions: 1

Hamster playing table tennis

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

#30 Muse Spark Open

high
Cost
$0.045
Time
239.2s
Tokens
10,710 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 Spark OpenhighvsSeed 2.1 TurbolowMuse Spark OpenhighvsClaude Opus 5.5mediumMuse Spark OpenhighvsClaude Opus 5mediumMuse Spark OpenhighvsMuse WondermediumMuse Spark OpenhighvsClaude Opus 5highMuse Spark OpenhighvsGPT-5.5mediumMuse Spark OpenhighvsGemini 3.7 FlashlowMuse Spark OpenhighvsClaude Sonnet 5.5maxMuse Spark OpenhighvsClaude Opus 5.5highMuse Spark OpenhighvsQwen3.8 MAXmedium

Category Breakdown

Category Score Consistency Tests Correct
Agentic 10.0 10.0
Anti-AI Tricks 8.3 10.0
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 3.6 7.2
General Intelligence 10.0 10.0
Instructions following 9.8 10.0
Puzzle Solving 7.9 9.9
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models