GPT 6 Sol medium leads on quality and agent time: 7.6 points higher and 3.9× faster; GPT 6 Luna max leads on cost: 8.0× cheaper.
Stet score
GPT 6 Luna maxRank 8 of 14
50.095% range 40.1–59.3
GPT 6 Sol mediumRank 7 of 14
57.695% range 49.5–65.77.6 points higher
GPT 6 Luna max solved 0 tasks that GPT 6 Sol medium didn’t, and GPT 6 Sol medium solved 2 that GPT 6 Luna max didn’t. Both solved 12; neither solved 10.
stet-15439c21Passed testsstet-6f84e978Passed 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 | GPT 6 Sol medium | 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 | GPT 6 Sol medium 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 | GPT 6 Sol medium only |
stet-commit-f8ae1177 | Passed tests | Passed tests | Both |
stet-2450ca2d | Failed | Failed | Neither |
stet-commit-342d0ac0 | Equivalent to the merged fix | Equivalent to the merged fix | Both |
stet-commit-60a0e6c2 | Failed | Failed | Neither |
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 | GPT 6 Sol medium |
|---|---|---|
| Rank | 8 of 14 | 7 of 14 |
| Stet score | 50.095% range 40.1–59.3 | 57.695% range 49.5–65.7 |
| Solved | 12/248 passed, 4 judged equivalent | 14/2411 passed, 3 judged equivalent |
| Passed review | 6/24 | 8/24 |
| Matched merged change | 11/24 | 10/24 |
| Cost / task | $0.37 | $3.01 |
| How cost was recorded | reported by its harness | estimated from tokens |
| Agent time / task | 59.7 min | 15.4 min |
| Ran in | Daytona sandbox | Daytona sandbox |
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.
GPT 6 Luna max matched the merged change more often: 7 of 11 to GPT 6 Sol medium’s 6.
| GPT 6 Luna max | GPT 6 Sol medium | |
|---|---|---|
| Matched merged change | 7/11 | 6/11 |
| Passed review | 6/11 | 6/11 |
| Cost / task | $0.09 | $0.75 |
| Agent time / task | 19.0 min | 6.6 min |
7 tasks
7 tasks whose instructions start with “Fix”. Their merged changes were 4–29 lines in 1–2 files.
Both matched the merged change on 5 of 7.
GPT 6 Sol medium passed review more often: 5 of 7 to GPT 6 Luna max’s 4.
| GPT 6 Luna max | GPT 6 Sol medium | |
|---|---|---|
| Matched merged change | 5/7 | 5/7 |
| Passed review | 4/7 | 5/7 |
| Cost / task | $0.08 | $0.60 |
| Agent time / task | 17.1 min | 5.4 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.
Both matched the merged change on 4 of 13.
GPT 6 Sol medium passed review more often: 2 of 13 to GPT 6 Luna max’s 0.
| GPT 6 Luna max | GPT 6 Sol medium | |
|---|---|---|
| Matched merged change | 4/13 | 4/13 |
| Passed review | 0/13 | 2/13 |
| Cost / task | $0.61 | $4.92 |
| Agent time / task | 94.2 min | 22.9 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.