SWE-2 Max leads on quality: 35.4 points higher; GLM 5.3 Flash leads on agent time: 2.6× faster; SWE-2 Max’s cost wasn’t recorded.
Stet score
GLM 5.3 FlashRank 13 of 14
31.095% range 21.5–41.5
SWE-2 MaxRank 1 of 14
66.495% range 56.8–75.435.4 points higher
GLM 5.3 Flash solved 0 tasks that SWE-2 Max didn’t, and SWE-2 Max solved 7 that GLM 5.3 Flash didn’t. Both solved 9; neither solved 8.
stet-commit-5d766ddePassed testsstet-6f84e978Passed testsstet-2450ca2dPassed testsstet-commit-342d0ac0Equivalent to the merged fixstet-commit-60a0e6c2Passed testsstet-commit-5e075641Passed testsstet-commit-a8716b88Equivalent 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 | GLM 5.3 Flash | SWE-2 Max | 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 | Equivalent to the merged fix | Both |
stet-66762b4c | Passed tests | Passed tests | Both |
stet-commit-f0caded9 | Passed tests | Passed tests | Both |
stet-commit-5d766dde | Failed | Passed tests | SWE-2 Max only |
stet-43493c52 | Failed | Failed | Neither |
stet-6f84e978 | Failed | Passed tests | SWE-2 Max only |
stet-commit-f8ae1177 | Failed | Failed | Neither |
stet-2450ca2d | Failed | Passed tests | SWE-2 Max only |
stet-commit-342d0ac0 | Failed | Equivalent to the merged fix | SWE-2 Max only |
stet-commit-60a0e6c2 | Failed | Passed tests | SWE-2 Max only |
stet-commit-5e075641 | Failed | Passed tests | SWE-2 Max only |
stet-commit-2826765e | Failed | Failed | Neither |
stet-commit-a8716b88 | Failed | Equivalent to the merged fix | SWE-2 Max only |
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 | GLM 5.3 Flash | SWE-2 Max |
|---|---|---|
| Rank | 13 of 14 | 1 of 14 |
| Stet score | 31.095% range 21.5–41.5 | 66.495% range 56.8–75.4 |
| Solved | 9/249 passed, 0 judged equivalent | 16/2413 passed, 3 judged equivalent |
| Passed review | 6/231 not recorded | 8/24 |
| Matched merged change | 6/24 | 13/24 |
| Cost / task | $0.41 | not recorded |
| How cost was recorded | estimated from tokens | not recorded |
| Agent time / task | 26.7 min | 68.3 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.
SWE-2 Max matched the merged change more often: 8 of 11 to GLM 5.3 Flash’s 6.
| GLM 5.3 Flash | SWE-2 Max | |
|---|---|---|
| Matched merged change | 6/11 | 8/11 |
| Passed review | 6/101 not recorded | 7/11 |
| Cost / task | $0.06 | not recorded |
| Agent time / task | 10.2 min | 22.1 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.
| GLM 5.3 Flash | SWE-2 Max | |
|---|---|---|
| Matched merged change | 5/7 | 5/7 |
| Passed review | 5/7 | 5/7 |
| Cost / task | $0.05 | not recorded |
| Agent time / task | 9.4 min | 21.5 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.
SWE-2 Max matched the merged change more often: 5 of 13 to GLM 5.3 Flash’s 0.
| GLM 5.3 Flash | SWE-2 Max | |
|---|---|---|
| Matched merged change | 0/13 | 5/13 |
| Passed review | 0/13 | 1/13 |
| Cost / task | $0.70 | not recorded |
| Agent time / task | 40.7 min | 107.3 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.