Advertise here
#30

Muse Spark 1.2

Meta Release: 2026-08-06 Tested on: 2026-08-05 23:32 meta/muse-spark-1.2::low
~1T total (~50B active)MoEClosedEstimated
(high) (medium) (low)

Summary

Muse Spark 1.2 scores 8.4 on AI BENCHY and ranks #30. It has 9.9 reliability, a 77.3% pass rate, $0.650 total cost, and 9.67s average response time.

What makes Muse Spark 1.2 unique: Its total benchmark cost is unusually low for its score range.

Model facts

Researched on 2026-08-12

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

Best estimate from public evidence; the vendor did not disclose every value. API-only exact checkpoint; promised weights were not public at research time.

Parameter source Availability source

Score

8.4

Consistency

9.0

Reliability

9.9

Total Cost (Current Price)

$0.650

Total Output Tokens

122,939

Total Input Tokens

101,802

Input Price

$1.250 / 1M

Output Price

$4.250 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 77.3%

Flaky tests

3

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

Response Time (avg)

9.67s

Response Time (max): 47.80s

Response Time (total): 212.82s

Wrong answer: 4 Did not follow instructions: 3

Hamster playing table tennis

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

#30 Muse Spark 1.2

low
Cost
$0.019
Time
14.6s
Tokens
4,384 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 03:27 Re-test 8.4 10.0 $0.655 Compare
2026-08-05 23:32 Initial run 8.4 9.9 $0.650 Current run

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-08-05 23:34 $1.250 / 1M $4.250 / 1M

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 1.2lowvsGrok 4.5mediumMuse Spark 1.2lowvsGrok 4.6mediumMuse Spark 1.2lowvsDeepSeek V4.1 FlashmediumMuse Spark 1.2lowvsGrok 4.5lowMuse Spark 1.2lowvsDeepSeek V4.1 FlashhighMuse Spark 1.2lowvsGPT-5.2mediumMuse Spark 1.2lowvsDeepSeek V4.1 FlashlowMuse Spark 1.2lowvsQwen3.8 27BhighMuse Spark 1.2lowvsGPT-5.4mediumMuse Spark 1.2lowvsSeed 2.1 Turbomedium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 9.2 8.4
Coding 8.4 7.4
Combined 9.8 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 5.0 10.0
Instructions following 9.8 10.0
Puzzle Solving 8.7 7.7
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models