Navigate
Advertise here

Ember-1 (high) vs Muse Glimmer 30B (low)

Muse Glimmer 30B (low) leads on average score with 7.1 vs 7.1. Muse Glimmer 30B (low) has the lower benchmark cost at $0.152 vs $1.798. Muse Glimmer 30B (low) is faster at 18.64s vs 56.77s, with pass rates of 71.2% vs 63.6%.

Last updated at: 2026-09-28

Compared models

Rank
#158
Total Output Tokens
110,125
Response Time (avg)
56.77s
Total Cost
$1.798
Rank
#154
Total Output Tokens
95,970
Response Time (avg)
18.64s
Total Cost
$0.152
Recommended model Muse Glimmer 30B (low)

It has the best score here (7.1), while costing about 11.9x less than Ember-1 (high).

Detailed comparison

Metric Ember-1 Ember-1 high Release: 2026-09-28 Muse Glimmer 30B Muse Glimmer 30B low Release: 2026-08-11
Score 7.1 7.1
Rank #158 #154
Reliability 8.0 10.0
Consistency 7.3 8.2
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 71.2% 63.6%
Flaky tests 7 5
Total Runs 66 66
Cost per result 14.981 1.692
Total Cost $1.798 $0.152
Input Price $3.000 / 1M $0.300 / 1M
Output Price $15.000 / 1M $1.200 / 1M
Total Input Tokens 48,577 130,312
Output Tokens 7,345 33,867
Reasoning Tokens 102,780 62,103
Response Time (avg) 56.77s 18.64s
Response Time (max) 255.06s 234.92s
Response Time (total) 1248.88s 410.18s
Parameters ~2.8T total (~104B active) 30B
Availability Closed Open source

Model generation showcase

Hamster playing table tennis

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

#158 Ember-1

high
Cost
$0.038
Time
55.1s
Tokens
2,671 tok

#154 Muse Glimmer 30B

low
Cost
$0.002
Time
13.5s
Tokens
953 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
Ember-1 8.2 7.2 88.9% 1 72.23s 7,144 1,281 23,093
Muse Glimmer 30B 8.1 9.9 66.7% 0 16.52s 7,419 2,759 10,173

Quick Compare

Switch Comparison Pair