GPT 6 Luna max leads on quality and cost: 9.8 points higher and 18.8× cheaper; Opus 4.8 leads on agent time: 2.6× faster.
Stet score
GPT 6 Luna maxRank 8 of 14
50.095% range 40.1–59.39.8 points higher
Opus 4.8Rank 11 of 14
40.295% range 30.3–50.3
GPT 6 Luna max solved 2 tasks that Opus 4.8 didn’t, and Opus 4.8 solved 3 that GPT 6 Luna max didn’t. Both solved 10; neither solved 9.
stet-commit-f8ae1177Passed testsstet-commit-342d0ac0Equivalent to the merged fixstet-15439c21Passed testsstet-6f84e978Passed testsstet-commit-60a0e6c2Passed testsA 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.
| Task | GPT 6 Luna max | Opus 4.8 | Solved by |
|---|---|---|---|
stet-3169aefa | Passed tests | Passed tests | Both |
stet-89dfbc27 | Passed tests | Passed tests | Both |
stet-b28f4fe7 | Passed tests | Passed tests | Both |
stet-232b50ba | Passed tests | Passed tests | Both |
stet-5276aa3f | Passed tests | Passed tests | Both |
stet-commit-bbbbae09 | Passed tests | Passed tests | Both |
stet-15439c21 | Failed | Passed tests | Opus 4.8 only |
stet-66762b4c | Equivalent to the merged fix | Passed tests | Both |
stet-commit-f0caded9 | Equivalent to the merged fix | Equivalent to the merged fix | Both |
stet-commit-5d766dde | Equivalent to the merged fix | Equivalent to the merged fix | Both |
stet-43493c52 | Passed tests | Passed tests | Both |
stet-6f84e978 | Failed | Passed tests | Opus 4.8 only |
stet-commit-f8ae1177 | Passed tests | Failed | GPT 6 Luna max only |
stet-2450ca2d | Failed | Failed | Neither |
stet-commit-342d0ac0 | Equivalent to the merged fix | Failed | GPT 6 Luna max only |
stet-commit-60a0e6c2 | Failed | Passed tests | Opus 4.8 only |
stet-commit-5e075641 | Failed | Failed | Neither |
stet-commit-2826765e | Failed | Failed | Neither |
stet-commit-a8716b88 | Failed | Failed | Neither |
stet-commit-30506f8e | Failed | Failed | Neither |
stet-commit-87814583 | Failed | Failed | Neither |
stet-commit-d2ab0c25 | Failed | Failed | Neither |
stet-commit-e41c2e2d | Failed | Failed | Neither |
stet-commit-e928166f | Failed | Failed | Neither |
| Metric | GPT 6 Luna max | Opus 4.8 |
|---|---|---|
| Rank | 8 of 14 | 11 of 14 |
| Stet score | 50.095% range 40.1–59.3 | 40.295% range 30.3–50.3 |
| Solved | 12/248 passed, 4 judged equivalent | 13/2411 passed, 2 judged equivalent |
| Passed review | 6/24 | 8/231 not recorded |
| Matched merged change | 11/24 | 11/24 |
| Cost / task | $0.37 | $7.05 |
| How cost was recorded | reported by its harness | reported by its harness |
| Agent time / task | 59.7 min | 23.3 min |
| Ran in | Daytona sandbox | local Docker |
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.
11 tasks
11 tasks whose merged change was 2–149 lines in 1–2 files. The 7 small fixes below are among them.
Opus 4.8 matched the merged change more often: 9 of 11 to GPT 6 Luna max’s 7.
| GPT 6 Luna max | Opus 4.8 | |
|---|---|---|
| Matched merged change | 7/11 | 9/11 |
| Passed review | 6/11 | 8/11 |
| Cost / task | $0.09 | $1.41 |
| Agent time / task | 19.0 min | 12.8 min |
7 tasks
7 tasks whose instructions start with “Fix”. Their merged changes were 4–29 lines in 1–2 files.
Opus 4.8 matched the merged change more often: 7 of 7 to GPT 6 Luna max’s 5.
| GPT 6 Luna max | Opus 4.8 | |
|---|---|---|
| Matched merged change | 5/7 | 7/7 |
| Passed review | 4/7 | 7/7 |
| Cost / task | $0.08 | $1.17 |
| Agent time / task | 17.1 min | 9.7 min |
13 tasks
13 tasks whose merged change ran over 150 lines or more than 3 files: 113–1,420 lines in 2–19 files.
GPT 6 Luna max matched the merged change more often: 4 of 13 to Opus 4.8’s 2.
| GPT 6 Luna max | Opus 4.8 | |
|---|---|---|
| Matched merged change | 4/13 | 2/13 |
| Passed review | 0/13 | 0/121 not recorded |
| Cost / task | $0.61 | $11.83 |
| Agent time / task | 94.2 min | 32.2 min |
Stet replays your merged PRs, scores quality above pass/fail, and delivers comparison reports through your agent.
Run it on your repocompare-n24-r3b.