Navigate
Advertise here

Muse Glimmer 30B (xhigh) vs Muse Spark 1.1 (high)

The average score is effectively tied at 8.4 vs 8.4. Muse Glimmer 30B (xhigh) has the lower benchmark cost at $0.585 vs $2.570. Muse Spark 1.1 (high) is faster at 37.41s vs 97.70s, with pass rates of 71.0% vs 69.6%.

Last updated at: 2026-11-10

Compared models

Rank
#106
Total Output Tokens
415,435
Response Time (avg)
97.70s
Total Cost
$0.585
Rank
#109
Total Output Tokens
505,566
Response Time (avg)
37.41s
Total Cost
$2.570
Recommended model Muse Glimmer 30B (xhigh)

It has the best score here (8.4), while costing about 4.4x less than Muse Spark 1.1 (high).

Detailed comparison

Metric Muse Glimmer 30B Muse Glimmer 30B xhigh Release: 2026-08-11 Muse Spark 1.1 Muse Spark 1.1 high Release: 2026-07-16
Score 8.4 8.4
Rank #106 #109
Reliability 9.9 10.0
Consistency 8.6 8.0
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 71.0% 69.6%
Flaky tests 4 6
Total Runs 69 69
Cost per result 5.170 19.762
Total Cost $0.585 $2.570
Input Price $0.300 / 1M $1.250 / 1M
Output Price $1.200 / 1M $4.250 / 1M
Cache Read Price $0.040 / 1M $0.150 / 1M
Cache Write Price N/A N/A
Total Input Tokens 287,538 336,310
Output Tokens 118,266 10,838
Reasoning Tokens 346,758 494,728
Response Time (avg) 97.70s 37.41s
Response Time (max) 576.79s 196.03s
Response Time (total) 2247.18s 860.39s
Parameters 30B ~1T total (~50B active)
Availability Open source Closed

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

Model generation showcase

Hamster playing table tennis

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

#106 Muse Glimmer 30B

xhigh
Cost
$0.007
Time
94.6s
Tokens
4,318 tok

#109 Muse Spark 1.1

high
Cost
$0.039
Time
50.1s
Tokens
9,423 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 Glimmer 30B 10.0 10.0 100.0% 0 105.91s 7,428 18,697 63,334
Muse Spark 1.1 10.0 10.0 100.0% 0 22.92s 8,562 349 36,039

Switch Comparison Pair