Skip to the comparison
STET
Join the waitlist

Haiku 5.5 max vs SWE-2 Max high

No clear quality winner: SWE-2 Max high won 7, Haiku 5.5 max won 3, 13 tied, 1 undecided; Haiku 5.5 max leads on agent time: 1.2× faster; SWE-2 Max high’s cost wasn’t recorded.

24 tasksData from

Stet score

Haiku 5.5 maxclaude-code · max reasoningRank 8 of 16

55.595% range 44.6–65.7

SWE-2 Max highdevin · high reasoningRank 3 of 16

64.395% range 54.3–73.98.8 points higher

A directional read: their 95% score ranges overlap.

Cost / task

Haiku 5.5 max$3.85
SWE-2 Max highnot recorded

Agent time / task

Haiku 5.5 max58.4 min1.2× faster
SWE-2 Max high68.3 min

Quality

Head-to-head matchups

Haiku 5.5 max won3

Tied131 undecided

SWE-2 Max high won7

SWE-2 Max high’s win share 58%, 95% range 43–72%Ties are within judge noise.

Task by task

Haiku 5.5 max solved 1 task that SWE-2 Max high didn’t, and SWE-2 Max high solved 4 that Haiku 5.5 max didn’t. Both solved 11; neither solved 7.

Haiku 5.5 max only 1

  • stet-commit-f8ae1177Passed tests

SWE-2 Max high only 4

  • stet-232b50baPassed tests
  • stet-66762b4cPassed tests
  • stet-commit-5e075641Passed tests
  • stet-commit-a8716b88Equivalent to the merged fix

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. 1 of the 24 tasks is left out because one of the two has no scored result on it.

All 23 compared tasks
Task by task
TaskHaiku 5.5 maxSWE-2 Max highSolved by
stet-3169aefaPassed testsPassed testsBoth
stet-89dfbc27Passed testsPassed testsBoth
stet-b28f4fe7Passed testsPassed testsBoth
stet-232b50baFailedPassed testsSWE-2 Max high only
stet-5276aa3fPassed testsPassed testsBoth
stet-commit-bbbbae09Passed testsPassed testsBoth
stet-66762b4cFailedPassed testsSWE-2 Max high only
stet-15439c21Passed testsEquivalent to the merged fixBoth
stet-commit-5d766ddeEquivalent to the merged fixPassed testsBoth
stet-43493c52FailedFailedNeither
stet-commit-f0caded9Passed testsPassed testsBoth
stet-6f84e978Equivalent to the merged fixPassed testsBoth
stet-2450ca2dPassed testsPassed testsBoth
stet-commit-342d0ac0Equivalent to the merged fixEquivalent to the merged fixBoth
stet-commit-f8ae1177Passed testsFailedHaiku 5.5 max only
stet-commit-5e075641FailedPassed testsSWE-2 Max high only
stet-commit-2826765eFailedFailedNeither
stet-commit-a8716b88FailedEquivalent to the merged fixSWE-2 Max high only
stet-commit-e928166fFailedFailedNeither
stet-commit-30506f8eFailedFailedNeither
stet-commit-87814583FailedFailedNeither
stet-commit-d2ab0c25FailedFailedNeither
stet-commit-e41c2e2dFailedFailedNeither

Side by side

Side by side
MetricHaiku 5.5 maxSWE-2 Max high
Harnessclaude-codedevin
Reasoning effortmaxhigh
Rank8 of 163 of 16
Stet score55.595% range 44.6–65.764.395% range 54.3–73.9
Solved12/249 passed, 3 judged equivalent16/2413 passed, 3 judged equivalent
Cost / task$3.85not recorded
Agent time / task58.4 min68.3 min

See which setup wins on your repo

Stet replays your merged PRs, scores quality above pass/fail, and delivers comparison reports through your agent.

Run it on your repo

About this data

  • 24 tasks, each a merged change replayed from the repo as it was just before the merge.
  • Data from .
  • Both setups come from the same leaderboard run of 16 setups: bmk_d4ba310fdf50db4ccb2092e3.

See all 16 setups on the leaderboardHow Stet measures