Navigate
Advertise here

Muse Spark 1.3 (low) vs GPT-6 Luna (high)

GPT-6 Luna (high) leads on average score with 8.3 vs 8.2. GPT-6 Luna (high) has the lower benchmark cost at $0.054 vs $0.689. Muse Spark 1.3 (low) is faster at 16.03s vs 17.53s, with pass rates of 81.8% vs 75.8%.

Last updated at: 2026-09-23

Compared models

Rank
#76
Total Output Tokens
127,711
Response Time (avg)
16.03s
Total Cost
$0.689
Rank
#73
Total Output Tokens
91,405
Response Time (avg)
17.53s
Total Cost
$0.054
Recommended model GPT-6 Luna (high)

It has the best score here (8.3), while costing about 12.8x less than Muse Spark 1.3 (low).

Detailed comparison

Metric Muse Spark 1.3 Muse Spark 1.3 low Release: 2026-09-02 GPT-6 Luna GPT-6 Luna high Release: 2026-09-23
Score 8.2 8.3
Rank #76 #73
Reliability 10.0 10.0
Consistency 8.1 9.0
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 81.8% 75.8%
Flaky tests 5 3
Total Runs 66 66
Cost per result 4.594 0.359
Total Cost $0.689 $0.054
Input Price $1.250 / 1M $0.100 / 1M
Output Price $4.250 / 1M $0.500 / 1M
Total Input Tokens 116,947 80,441
Output Tokens 11,026 4,761
Reasoning Tokens 116,685 86,644
Response Time (avg) 16.03s 17.53s
Response Time (max) 78.72s 106.93s
Response Time (total) 352.69s 385.74s
Parameters ~1T total (~50B active) ~400B total (~17B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

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

#76 Muse Spark 1.3

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

#73 GPT-6 Luna

high
Cost
$0.003
Time
49.2s
Tokens
5,231 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 8.2 7.2 88.9% 1 20.86s 5,958 795 19,077
GPT-6 Luna 7.8 7.4 77.8% 1 24.69s 7,302 483 15,691

Quick Compare

Switch Comparison Pair