Skip to the comparison
STET
Get a free trial

GPT 6 Luna low vs Muse control

Muse control leads on quality: 12.0 points higher; GPT 6 Luna low leads on cost and agent time: 1.9× cheaper and 1.9× faster.

24 tasksData from

Stet score

GPT 6 Luna lowRank 14 of 14

21.295% range 12.5–31.2

Muse controlRank 12 of 14

33.295% range 24.3–42.412.0 points higher

A directional read: their 95% score ranges overlap.

Cost / task

GPT 6 Luna low$0.051.9× cheaper
Muse control$0.10

Agent time / task

GPT 6 Luna low6.9 min1.9× faster
Muse control13.2 min

Task by task

GPT 6 Luna low solved 1 task that Muse control didn’t, and Muse control solved 6 that GPT 6 Luna low didn’t. Both solved 4; neither solved 12.

GPT 6 Luna low only 1

  • stet-15439c21Passed tests

Muse control only 6

  • stet-5276aa3fPassed tests
  • stet-commit-bbbbae09Passed tests
  • stet-66762b4cPassed tests
  • stet-commit-5d766ddeEquivalent to the merged fix
  • stet-43493c52Passed tests
  • stet-2450ca2dEquivalent to the merged fix

A task counts as solved when its tests passed or a judge found the fix equivalent to the merged change, as in the leaderboard’s Solved column. Stet score also weighs code quality, so it can order the two differently. 1 of the 24 tasks is left out because one of the two has no scored result on it.

All 23 compared tasks
Task by task
TaskGPT 6 Luna lowMuse controlSolved by
stet-3169aefaPassed testsPassed testsBoth
stet-89dfbc27Passed testsPassed testsBoth
stet-b28f4fe7Passed testsPassed testsBoth
stet-232b50baPassed testsPassed testsBoth
stet-5276aa3fFailedPassed testsMuse control only
stet-commit-bbbbae09No change madePassed testsMuse control only
stet-15439c21Passed testsFailedGPT 6 Luna low only
stet-66762b4cFailedPassed testsMuse control only
stet-commit-f0caded9FailedFailedNeither
stet-commit-5d766ddeNo change madeEquivalent to the merged fixMuse control only
stet-43493c52FailedPassed testsMuse control only
stet-6f84e978FailedFailedNeither
stet-commit-f8ae1177No change madeFailedNeither
stet-2450ca2dFailedEquivalent to the merged fixMuse control only
stet-commit-342d0ac0FailedFailedNeither
stet-commit-5e075641FailedFailedNeither
stet-commit-2826765eFailedFailedNeither
stet-commit-a8716b88FailedFailedNeither
stet-commit-30506f8eFailedFailedNeither
stet-commit-87814583FailedFailedNeither
stet-commit-d2ab0c25FailedFailedNeither
stet-commit-e41c2e2dFailedFailedNeither
stet-commit-e928166fFailedFailedNeither

Side by side

Side by side
MetricGPT 6 Luna lowMuse control
Rank14 of 1412 of 14
Stet score21.295% range 12.5–31.233.295% range 24.3–42.4
Solved5/245 passed, 0 judged equivalent10/248 passed, 2 judged equivalent
Passed review5/204 not recorded5/24
Matched merged change5/204 not recorded8/24
Cost / task$0.05$0.10
How cost was recordedreported by its harnessestimated from tokens
Agent time / task6.9 min13.2 min
Ran inDaytona sandboxlocal Docker

Where each setup is the better choice

The leaderboard’s readings on groups of tasks. Each group holds fewer tasks than the overall standings, so treat these as leads to test on your repo.

Changes up to 150 lines

11 tasks

11 tasks whose merged change was 2–149 lines in 1–2 files. The 7 small fixes below are among them.

Muse control matched the merged change more often: 7 of 11 to GPT 6 Luna low’s 5.

Changes up to 150 lines
GPT 6 Luna lowMuse control
Matched merged change5/117/11
Passed review5/115/11
Cost / task$0.02$0.03
Agent time / task2.1 min4.3 min

Small fixes

7 tasks

7 tasks whose instructions start with “Fix”. Their merged changes were 4–29 lines in 1–2 files.

GPT 6 Luna low matched the merged change more often: 5 of 7 to Muse control’s 4.

Small fixes
GPT 6 Luna lowMuse control
Matched merged change5/74/7
Passed review5/74/7
Cost / task$0.01$0.03
Agent time / task2.1 min4.3 min

Larger changes

13 tasks

13 tasks whose merged change ran over 150 lines or more than 3 files: 113–1,420 lines in 2–19 files.

Larger changes
GPT 6 Luna lowMuse control
Matched merged change0/94 not recorded1/13
Passed review0/94 not recorded0/13
Cost / task$0.08$0.16
Agent time / task11.0 min20.8 min

See which setup wins on your repo

Stet replays your merged PRs, scores quality above pass/fail, and delivers comparison reports through your agent.

Run it on your repo

About this data

  • 24 tasks, each a merged change replayed from the repo as it was just before the merge.
  • Data from .
  • Both setups come from the same leaderboard run of 14 setups: compare-n24-r3b.

See all 14 setups on the leaderboardHow Stet measures