GPT 6.1 Sol medium leads on quality: 44.1 points higher; GPT 6 Luna low leads on cost and agent time: 20.6× cheaper and 1.7× faster.
Stet score
GPT 6.1 Sol mediumRank 2 of 14
65.395% range 55.6–74.644.1 points higher
GPT 6 Luna lowRank 14 of 14
21.295% range 12.5–31.2
GPT 6.1 Sol medium solved 8 tasks that GPT 6 Luna low didn’t, and GPT 6 Luna low solved 0 that GPT 6.1 Sol medium didn’t. Both solved 5; neither solved 10.
stet-5276aa3fPassed testsstet-commit-bbbbae09Passed testsstet-66762b4cPassed testsstet-commit-5d766ddeEquivalent to the merged fixstet-43493c52Passed testsstet-6f84e978Equivalent to the merged fixstet-commit-f8ae1177Passed testsstet-commit-342d0ac0Equivalent to the merged fixA 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.
| Task | GPT 6.1 Sol medium | GPT 6 Luna low | 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 | Failed | GPT 6.1 Sol medium only |
stet-commit-bbbbae09 | Passed tests | No change made | GPT 6.1 Sol medium only |
stet-15439c21 | Passed tests | Passed tests | Both |
stet-66762b4c | Passed tests | Failed | GPT 6.1 Sol medium only |
stet-commit-f0caded9 | Failed | Failed | Neither |
stet-commit-5d766dde | Equivalent to the merged fix | No change made | GPT 6.1 Sol medium only |
stet-43493c52 | Passed tests | Failed | GPT 6.1 Sol medium only |
stet-6f84e978 | Equivalent to the merged fix | Failed | GPT 6.1 Sol medium only |
stet-commit-f8ae1177 | Passed tests | No change made | GPT 6.1 Sol medium only |
stet-2450ca2d | Failed | Failed | Neither |
stet-commit-342d0ac0 | Equivalent to the merged fix | Failed | GPT 6.1 Sol medium 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 6.1 Sol medium | GPT 6 Luna low |
|---|---|---|
| Rank | 2 of 14 | 14 of 14 |
| Stet score | 65.395% range 55.6–74.6 | 21.295% range 12.5–31.2 |
| Solved | 13/2410 passed, 3 judged equivalent | 5/245 passed, 0 judged equivalent |
| Passed review | 10/24 | 5/204 not recorded |
| Matched merged change | 10/24 | 5/204 not recorded |
| Cost / task | $1.10 | $0.05 |
| How cost was recorded | estimated from tokens | reported by its harness |
| Agent time / task | 11.8 min | 6.9 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 6.1 Sol medium matched the merged change more often: 7 of 11 to GPT 6 Luna low’s 5.
| GPT 6.1 Sol medium | GPT 6 Luna low | |
|---|---|---|
| Matched merged change | 7/11 | 5/11 |
| Passed review | 8/11 | 5/11 |
| Cost / task | $0.47 | $0.02 |
| Agent time / task | 5.8 min | 2.1 min |
7 tasks
7 tasks whose instructions start with “Fix”. Their merged changes were 4–29 lines in 1–2 files.
GPT 6.1 Sol medium matched the merged change more often: 6 of 7 to GPT 6 Luna low’s 5.
| GPT 6.1 Sol medium | GPT 6 Luna low | |
|---|---|---|
| Matched merged change | 6/7 | 5/7 |
| Passed review | 5/7 | 5/7 |
| Cost / task | $0.42 | $0.01 |
| Agent time / task | 5.3 min | 2.1 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 6.1 Sol medium | GPT 6 Luna low | |
|---|---|---|
| Matched merged change | 3/13 | 0/94 not recorded |
| Passed review | 2/13 | 0/94 not recorded |
| Cost / task | $1.63 | $0.08 |
| Agent time / task | 16.9 min | 11.0 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.