Navigate
AI BENCHY
Advertise here

Muse Spark 1.3 — high vs low

The average score is effectively tied at 9.0 vs 9.0. low has the lower benchmark cost at $0.633 vs $1.252. low is faster at 43.67s vs 117.06s, with pass rates of 81.8% vs 83.3%.

Last updated at: 2026-09-02

Rank
#24
Total Output Tokens
265,177
Response Time (avg)
117.06s
Total Cost
$1.252
Rank
#25
Total Output Tokens
117,915
Response Time (avg)
43.67s
Total Cost
$0.633
Recommended model low

It has the best score here (9.0), while costing about 2.0x less than Muse Spark 1.3 (high).

Detailed comparison

Metric Muse Spark 1.3 Muse Spark 1.3 high Release: 2026-09-02 Muse Spark 1.3 Muse Spark 1.3 low Release: 2026-09-02
Score 9.0 9.0
Rank #24 #25
Reliability 9.5 9.6
Consistency 8.9 9.0
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 81.8% 83.3%
Flaky tests 3 3
Total Runs 66 66
Cost per result 7.361 3.720
Total Cost $1.252 $0.633
Input Price $1.250 / 1M $1.250 / 1M
Output Price $4.250 / 1M $4.250 / 1M
Total Input Tokens 99,477 104,966
Output Tokens 14,053 10,208
Reasoning Tokens 251,124 107,707
Response Time (avg) 117.06s 43.67s
Response Time (max) 470.12s 190.38s
Response Time (total) 2575.43s 960.70s
Parameters ~1T total (~50B active) ~1T total (~50B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

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

#24 Muse Spark 1.3

high
Cost
$0.050
Time
203.3s
Tokens
11,679 tok

#25 Muse Spark 1.3

low
Cost
$0.017
Time
83.9s
Tokens
3,959 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Muse Spark 1.3 10.0 10.0 100.0% 0 146.96s 7,275 2,003 59,912
Muse Spark 1.3 10.0 10.0 100.0% 0 53.93s 7,275 1,047 21,679

Quick Compare

Switch Comparison Pair