Haiku 5.5 low leads on quality and agent time: 8.1 points higher and 1.3× faster; Muse control leads on cost: 2.5× cheaper.
Stet score
Haiku 5.5 lowRank 10 of 14
41.395% range 34.8–47.88.1 points higher
Muse controlRank 12 of 14
33.295% range 24.3–42.4
Haiku 5.5 low solved 2 tasks that Muse control didn’t, and Muse control solved 1 that Haiku 5.5 low didn’t. Both solved 9; neither solved 12.
stet-15439c21Equivalent to the merged fixstet-commit-f0caded9Equivalent to the merged fixstet-2450ca2dEquivalent 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.
| Task | Haiku 5.5 low | Muse control | 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 | Equivalent to the merged fix | Failed | Haiku 5.5 low only |
stet-66762b4c | Equivalent to the merged fix | Passed tests | Both |
stet-commit-f0caded9 | Equivalent to the merged fix | Failed | Haiku 5.5 low only |
stet-commit-5d766dde | Equivalent to the merged fix | Equivalent to the merged fix | Both |
stet-43493c52 | Passed tests | Passed tests | Both |
stet-6f84e978 | Failed | Failed | Neither |
stet-commit-f8ae1177 | Failed | Failed | Neither |
stet-2450ca2d | Failed | Equivalent to the merged fix | Muse control only |
stet-commit-342d0ac0 | Failed | Failed | Neither |
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 | Haiku 5.5 low | Muse control |
|---|---|---|
| Rank | 10 of 14 | 12 of 14 |
| Stet score | 41.395% range 34.8–47.8 | 33.295% range 24.3–42.4 |
| Solved | 11/247 passed, 4 judged equivalent | 10/248 passed, 2 judged equivalent |
| Passed review | 8/24 | 5/24 |
| Matched merged change | 9/24 | 8/24 |
| Cost / task | $0.25 | $0.10 |
| How cost was recorded | reported by its harness | estimated from tokens |
| Agent time / task | 9.9 min | 13.2 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.
Both matched the merged change on 7 of 11.
Haiku 5.5 low passed review more often: 7 of 11 to Muse control’s 5.
| Haiku 5.5 low | Muse control | |
|---|---|---|
| Matched merged change | 7/11 | 7/11 |
| Passed review | 7/11 | 5/11 |
| Cost / task | $0.02 | $0.03 |
| Agent time / task | 2.8 min | 4.3 min |
7 tasks
7 tasks whose instructions start with “Fix”. Their merged changes were 4–29 lines in 1–2 files.
Haiku 5.5 low matched the merged change more often: 5 of 7 to Muse control’s 4.
| Haiku 5.5 low | Muse control | |
|---|---|---|
| Matched merged change | 5/7 | 4/7 |
| Passed review | 5/7 | 4/7 |
| Cost / task | $0.01 | $0.03 |
| Agent time / task | 2.7 min | 4.3 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.
Haiku 5.5 low matched the merged change more often: 2 of 13 to Muse control’s 1.
| Haiku 5.5 low | Muse control | |
|---|---|---|
| Matched merged change | 2/13 | 1/13 |
| Passed review | 1/13 | 0/13 |
| Cost / task | $0.45 | $0.16 |
| Agent time / task | 15.9 min | 20.8 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.