GPT 6.1 Sol medium leads on quality, cost and agent time: 6.2 points higher, 11.3× cheaper and 3.3× faster.
Stet score
GPT 6.1 Sol mediumRank 2 of 14
65.395% range 55.6–74.66.2 points higher
Pareto 26.9Rank 5 of 14
59.195% range 48.8–69.2
GPT 6.1 Sol medium solved 2 tasks that Pareto 26.9 didn’t, and Pareto 26.9 solved 2 that GPT 6.1 Sol medium didn’t. Both solved 11; neither solved 9.
stet-commit-5d766ddeEquivalent to the merged fixstet-commit-342d0ac0Equivalent to the merged fixstet-commit-f0caded9Equivalent to the merged fixstet-2450ca2dPassed 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 6.1 Sol medium | Pareto 26.9 | 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 | Passed tests | Passed tests | Both |
stet-66762b4c | Passed tests | Passed tests | Both |
stet-commit-f0caded9 | Failed | Equivalent to the merged fix | Pareto 26.9 only |
stet-commit-5d766dde | Equivalent to the merged fix | Failed | GPT 6.1 Sol medium only |
stet-43493c52 | Passed tests | Passed tests | Both |
stet-6f84e978 | Equivalent to the merged fix | Passed tests | Both |
stet-commit-f8ae1177 | Passed tests | Passed tests | Both |
stet-2450ca2d | Failed | Passed tests | Pareto 26.9 only |
stet-commit-342d0ac0 | Equivalent to the merged fix | Failed | GPT 6.1 Sol medium only |
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 6.1 Sol medium | Pareto 26.9 |
|---|---|---|
| Rank | 2 of 14 | 5 of 14 |
| Stet score | 65.395% range 55.6–74.6 | 59.195% range 48.8–69.2 |
| Solved | 13/2410 passed, 3 judged equivalent | 13/2412 passed, 1 judged equivalent |
| Passed review | 10/24 | 8/24 |
| Matched merged change | 10/24 | 9/24 |
| Cost / task | $1.10 | $12.47 |
| How cost was recorded | estimated from tokens | reported by its harness on 23, estimated from tokens on 1 |
| Agent time / task | 11.8 min | 39.2 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.
Both matched the merged change on 7 of 11.
GPT 6.1 Sol medium passed review more often: 8 of 11 to Pareto 26.9’s 7.
| GPT 6.1 Sol medium | Pareto 26.9 | |
|---|---|---|
| Matched merged change | 7/11 | 7/11 |
| Passed review | 8/11 | 7/11 |
| Cost / task | $0.47 | $5.74 |
| Agent time / task | 5.8 min | 29.4 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 Pareto 26.9’s 4.
| GPT 6.1 Sol medium | Pareto 26.9 | |
|---|---|---|
| Matched merged change | 6/7 | 4/7 |
| Passed review | 5/7 | 5/7 |
| Cost / task | $0.42 | $5.42 |
| Agent time / task | 5.3 min | 30.6 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 matched the merged change more often: 3 of 13 to Pareto 26.9’s 2.
| GPT 6.1 Sol medium | Pareto 26.9 | |
|---|---|---|
| Matched merged change | 3/13 | 2/13 |
| Passed review | 2/13 | 1/13 |
| Cost / task | $1.63 | $18.18 |
| Agent time / task | 16.9 min | 47.4 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.