Navigate
Advertise here

Muse Ember (high) vs Muse Spark Open (high)

The average score is effectively tied at 9.2 vs 9.2. Muse Ember (high) has the lower benchmark cost at $0.156 vs $1.782. Muse Ember (high) is faster at 11.67s vs 151.96s, with pass rates of 79.7% vs 76.8%.

Last updated at: 2026-11-10

Compared models

Rank
#36
Total Output Tokens
254,892
Response Time (avg)
11.67s
Total Cost
$0.156
Rank
#37
Total Output Tokens
339,545
Response Time (avg)
151.96s
Total Cost
$1.782
Recommended model Muse Ember (high)

It has the best score here (9.2), while costing about 11.4x less than Muse Spark Open (high).

Detailed comparison

Metric Muse Ember Muse Ember high Release: 2026-11-09 Muse Spark Open Muse Spark Open high Release: 2026-10-15
Score 9.2 9.2
Rank #36 #37
Reliability 10.0 9.4
Consistency 9.6 9.6
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 79.7% 76.8%
Flaky tests 1 1
Total Runs 69 69
Cost per result 0.865 10.481
Total Cost $0.156 $1.782
Input Price $0.100 / 1M $1.250 / 1M
Output Price $0.500 / 1M $4.250 / 1M
Cache Read Price $0.004 / 1M $0.150 / 1M
Cache Write Price $0.125 / 1M N/A
Total Input Tokens 282,192 270,889
Output Tokens 14,054 10,688
Reasoning Tokens 240,838 328,857
Response Time (avg) 11.67s 151.96s
Response Time (max) 53.01s 960.01s
Response Time (total) 268.45s 3495.01s
Parameters ~150B total (~10B active) 816B total (42B active)
Availability Closed Weights available

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.

#36 Muse Ember

high
Cost
$0.005
Time
18.3s
Tokens
9,965 tok

#37 Muse Spark Open

high
Cost
$0.045
Time
239.2s
Tokens
10,710 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 Ember 10.0 10.0 100.0% 0 9.62s 7,410 1,213 34,691
Muse Spark Open 10.0 10.0 100.0% 0 33.49s 8,478 1,743 33,344

Quick Compare

Switch Comparison Pair

Claude Opus 5.5mediumvsMuse Spark OpenhighSeed 2.1 TurbolowvsMuse EmberhighMuse Spark OpenhighvsGPT-5.5mediumClaude Sonnet 5.5maxvsMuse Spark OpenhighMuse Spark OpenhighvsQwen3.8 MAXmediumDeepSeek V4.1 Flash 1017lowvsMuse Spark OpenhighClaude Opus 5.5mediumvsMuse EmberhighSeed 2.1 TurbolowvsMuse Spark OpenhighMuse EmberhighvsGPT-5.5mediumClaude Sonnet 5.5maxvsMuse EmberhighMuse EmberhighvsGPT-6.1 TerralowMuse EmberhighvsQwen3.8 MAXmedium