Pareto 26.9 medium leads on speed; SWE-2 max on cost; no clear quality difference. Different harnesses: Pareto 26.9 medium ran claude-code, SWE-2 max ran devin. This compares setups, not models alone.
Quality
Even
No clear difference
3–8 head to head, 13 tied
Speed
1.7× faster
Pareto 26.9 medium
39.2 min vs 68.3 min per task
Cost
2.2× cheaper
SWE-2 max
$2.76 vs $5.98 per task; $2.76 from 23/24 tasks
What this comparison is
1 real repositoryStet-AI/stet, private; not public benchmark scores
24 merged changeseach run end to end by the coding agent from the repo as it was before the change
Graded against the merged changeby the repo’s own tests and by judges comparing each patch with it
Quality, cost and timea smaller sample than public benchmarks, but real agent work on a real codebase
24 tasks · Data from
Stet score
Pareto 26.9 mediumclaude-code · medium reasoningRank 9 of 18
50.695% range 43.8–57.1
SWE-2 maxdevin · max reasoningRank 1 of 18
62.395% range 53.4–71.6
Other setups
Opus 5 medium
Opus 5 medium
60.9
Muse Wonder Full low
Muse Wonder Full low
57.2
GPT 6.1 Sol medium
GPT 6.1 Sol medium
53.1
GPT 6 Sol medium
GPT 6 Sol medium
52.9
Opus 4.8 medium
Opus 4.8 medium
52.5
Grok 4.7 high
Grok 4.7 high
50.9
DeepSeek V4.1 Flash max
DeepSeek V4.1 Flash max
50.9
GLM 5.3 Flash high
GLM 5.3 Flash high
49.0
DeepSeek V4.1 Flash (10/17) max
DeepSeek V4.1 Flash (10/17) max
48.4
Haiku 5.5 max
Haiku 5.5 max
48.0
GPT 6 Luna max
GPT 6 Luna max
47.7
Muse Spark 1.3 high
Muse Spark 1.3 high
47.7
GPT 5.6 Luna max
GPT 5.6 Luna max
45.4
GPT 5.6 Luna low
GPT 5.6 Luna low
44.7
Haiku 5.5 low
Haiku 5.5 low
43.7
GPT 6 Luna low
GPT 6 Luna low
39.8
304050607080even with the field
Their 95% score ranges overlap.
Quality
Head-to-head matchups
Pareto 26.9 medium won3
Tied13
SWE-2 max won8
SWE-2 max’s win share 61%, 95% range 48–73%Ties are within judge noise.
Other quality measures
Other quality measures
Metric
Pareto 26.9 medium
SWE-2 max
Code review pass rate
38%21 tasks
33%24 tasks
Checklist score
0.8024 tasks
0.8424 tasks
Equivalence rate
39%23 tasks
54%24 tasks
These measures are not part of the headline Stet score and carry no confidence interval, so a small gap may be noise. The marked side has the higher recorded value, not a proven lead.
Task by task
Pareto 26.9 medium solved 2 tasks that SWE-2 max didn’t, and SWE-2 max solved 7 that Pareto 26.9 medium didn’t. Both solved 9; neither solved 6.
On the 9 tasks both solved, judges preferred Pareto 26.9 medium’s patch on 1, SWE-2 max’s on 1, and called 7 even.
1,236 changed lines in 16 filesstet-commit-d2ab0c25
1,420 changed lines in 19 filesstet-commit-2826765e
Bar: changed lines in the merged change, log scale
A 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.
All 24 compared tasks
Task by task
Task
Pareto 26.9 medium
SWE-2 max
Solved by
Better patch
stet-89dfbc27 · 9 changed lines in 1 file
Passed tests$3.94 · 47.2 min
Passed tests$0.71 · 4.5 min
Both
Even
stet-b28f4fe7 · 29 changed lines in 1 file
Passed tests$3.17 · 22.7 min
Passed tests$2.02 · 16.7 min
Both
Even
stet-232b50ba · 10 changed lines in 1 file
Passed tests$3.09 · 42.8 min
Passed tests$1.56 · 11.9 min
Both
Even
stet-3169aefa · 6 changed lines in 1 file
Passed tests$2.42 · 14.8 min
Passed tests$1.03 · 5.3 min
Both
Even
stet-5276aa3f · 23 changed lines in 2 files
Passed tests$0.69 · 13.0 min
Passed tests$1.03 · 10.7 min
Both
Even
stet-66762b4c · 84 changed lines in 1 file
Passed tests$3.39 · 50.6 min
Passed tests$1.77 · 11.2 min
Both
Even
stet-commit-bbbbae09 · 941 changed lines in 7 files
Passed tests$14.28 · 95.4 min
Passed tests$0.61 · 89.7 min
Both
Pareto 26.9 medium
stet-commit-5d766dde · 218 changed lines in 2 files
Failed$1.02 · 7.0 min
Equivalent to the merged fix$4.04 · 20.0 min
SWE-2 max only
SWE-2 max
stet-43493c52 · 4 changed lines in 1 file
Passed tests$2.04 · 29.5 min
Failed$3.52 · 35.3 min
Pareto 26.9 medium only
Pareto 26.9 medium
stet-commit-f0caded9 · 113 changed lines in 4 files
Equivalent to the merged fix$8.97 · 60.8 min
Passed tests$3.91 · 22.6 min
Both
SWE-2 max
stet-15439c21 · 5 changed lines in 2 files
Failed$2.73 · 36.0 min
Passed tests$2.24 · 34.3 min
SWE-2 max only
SWE-2 max
stet-commit-f8ae1177 · 1,312 changed lines in 9 files
Passed tests$9.84 · 52.6 min
Failed300.0 min
Pareto 26.9 medium only
Pareto 26.9 medium
stet-2450ca2d · 2 changed lines in 1 file
Passed tests$0.61 · 12.3 min
Passed tests$1.18 · 11.8 min
Both
Even
stet-commit-342d0ac0 · 640 changed lines in 8 files
Failed$7.95 · 42.6 min
Equivalent to the merged fix$2.39 · 146.4 min
SWE-2 max only
SWE-2 max
stet-6f84e978 · 23 changed lines in 1 file
Failed$2.15 · 20.9 min
Passed tests$2.06 · 42.4 min
SWE-2 max only
SWE-2 max
stet-commit-5e075641 · 481 changed lines in 3 files
Failed$2.54 · 23.6 min
Passed tests$2.64 · 86.0 min
SWE-2 max only
SWE-2 max
stet-commit-60a0e6c2 · 552 changed lines in 11 files
Failed$5.64 · 20.5 min
Passed tests$0.66 · 106.1 min
SWE-2 max only
SWE-2 max
stet-commit-2826765e · 1,420 changed lines in 19 files
Failed$8.80 · 40.3 min
Failed$7.00 · 144.5 min
Neither
Even
stet-commit-a8716b88 · 564 changed lines in 10 files
Failed$13.86 · 42.7 min
Equivalent to the merged fix$1.29 · 102.3 min
SWE-2 max only
SWE-2 max
stet-commit-e928166f · 149 changed lines in 2 files
Failed$7.09 · 34.0 min
Failed$1.49 · 59.4 min
Neither
Even
stet-commit-30506f8e · 476 changed lines in 17 files
Failed$16.87 · 66.0 min
Failed$5.49 · 164.8 min
Neither
Even
stet-commit-87814583 · 763 changed lines in 8 files
Failed$11.99 · 89.0 min
Failed$5.19 · 73.6 min
Neither
Even
stet-commit-d2ab0c25 · 1,236 changed lines in 16 files
Failed$1.11 · 8.3 min
Failed$5.66 · 68.9 min
Neither
Even
stet-commit-e41c2e2d · 977 changed lines in 5 files
Failed$9.40 · 67.9 min
Failed$6.08 · 69.8 min
Neither
Even
Cost and time on each task
Each dot is one task, on a log scale: filled where the setup solved it, hollow where it didn’t. The line marks the median.
Cost per task
Pareto 26.9 mediummean $5.98 · median $3.66
SWE-2 maxmean $2.76 · median $2.06from 23/24 tasks
$0.50$1$2$5$10$20
SWE-2 max cost less on 17 of 23 tasks; Pareto 26.9 medium on 6.
Agent time per task
Pareto 26.9 mediummean 39.2 min · median 38.2 min
SWE-2 maxmean 68.3 min · median 50.9 min
1 min10 min100 min1000 min
Pareto 26.9 medium finished faster on 13 of 24 tasks; SWE-2 max on 11.
Where each setup is the better choice
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.
Small fixes
Cheaper here without solving fewer: SWE-2 max
10 tasks · 2–84 changed lines in 1–2 files
SWE-2 max solved more, 9 of 10 to 8, at 1.4× lower cost per task.
SWE-2 max was 1.6× faster.
Small fixes
Pareto 26.9 medium
SWE-2 max
Solved
8/10
9/10
Cost / task
$2.42
$1.71
Agent time / task
29.0 min
18.4 min
Large, cross-cutting changes
14 tasks · 113–1,420 changed lines in up to 19 files
SWE-2 max solved 7 of 14 to Pareto 26.9 medium’s 3.
Pareto 26.9 medium was 2.2× faster.
Large, cross-cutting changes
Pareto 26.9 medium
SWE-2 max
Solved
3/14
7/14
Cost / task
$8.53
$3.57from 13/14 tasks
Agent time / task
46.5 min
103.9 min
Side by side
Side by side
Metric
Pareto 26.9 medium
SWE-2 max
Harness
claude-code
devin
Reasoning effort
medium
max
Rank
9 of 18
1 of 18
Stet score
50.695% range 43.8–57.1
62.395% range 53.4–71.6
Solved
11/2410 passed, 1 judged equivalent
16/2413 passed, 3 judged equivalent
Cost / task
$5.98
$2.76from 23/24 tasks
Agent time / task
39.2 min
68.3 min
Questions
Which is better for coding, Pareto 26.9 medium or SWE-2 max?
No clear quality difference: SWE-2 max won 8, Pareto 26.9 medium won 3, 13 tied; SWE-2 max leads on cost: 2.2× cheaper; Pareto 26.9 medium leads on agent time: 1.7× faster. Measured on 24 merged changes from Stet-AI/stet.
How were Pareto 26.9 medium and SWE-2 max tested?
Both coding agents worked the same 24 merged changes from the private Stet-AI/stet repository, each in the real repo as it was before the change. The repo’s tests and judges graded every patch against the merged change; no public benchmark scores are used. Stet score: A setup’s average chance of beating another setup on a task, from 0 to 100; 50 is even with the field.
See which setup wins on your repo
Stet replays your merged changes, scores quality above pass/fail, and delivers comparison reports through your agent.