Navigate
Advertise here

Mercury 2.5 (high) vs Muse Glimmer 30B (low)

Muse Glimmer 30B (low) leads on average score with 7.1 vs 7.1. Mercury 2.5 (high) has the lower benchmark cost at $0.031 vs $0.143. Mercury 2.5 (high) is faster at 4.32s vs 18.64s, with pass rates of 62.1% vs 63.6%.

Last updated at: 2026-09-08

Compared models

Rank
#134
Total Output Tokens
174,547
Response Time (avg)
4.32s
Total Cost
$0.031
Rank
#131
Total Output Tokens
95,970
Response Time (avg)
18.64s
Total Cost
$0.143
Recommended model Mercury 2.5 (high)

Its score stays close to the best score here (7.1 vs 7.1), while costing about 4.6x less than Muse Glimmer 30B (low).

Detailed comparison

Metric Mercury 2.5 Mercury 2.5 high Release: 2026-09-08 Muse Glimmer 30B Muse Glimmer 30B low Release: 2026-08-11
Score 7.1 7.1
Rank #134 #131
Reliability 9.7 10.0
Consistency 8.6 8.2
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 62.1% 63.6%
Flaky tests 4 5
Total Runs 66 66
Cost per result 0.259 1.692
Total Cost $0.031 $0.143
Input Price $0.040 / 1M $0.300 / 1M
Output Price $0.150 / 1M $1.100 / 1M
Total Input Tokens 120,068 130,312
Output Tokens 3,402 33,867
Reasoning Tokens 171,145 62,103
Response Time (avg) 4.32s 18.64s
Response Time (max) 23.63s 234.92s
Response Time (total) 95.06s 410.18s
Parameters ~100B 30B
Availability Closed Open source

Model generation showcase

Hamster playing table tennis

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

#134 Mercury 2.5

high
Cost
$0.001
Time
3.5s
Tokens
2,447 tok

#131 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
Mercury 2.5 6.4 7.8 44.4% 1 6.58s 7,757 415 44,012
Muse Glimmer 30B 8.1 9.9 66.7% 0 16.52s 7,419 2,759 10,173

Quick Compare

Switch Comparison Pair