Skip to the comparison
STET
Get a free trial

Haiku 5.5 max vs Muse Wonder Full low

No clear quality winner: Muse Wonder Full low won 12, Haiku 5.5 max won 4, 3 tied, 5 undecided; Muse Wonder Full low leads on agent time: 2.7× faster; Muse Wonder Full low’s cost wasn’t recorded.

24 tasksData from

Stet score

Haiku 5.5 maxclaude-code · max reasoningRank 7 of 16

57.195% range 45.9–67.6

Muse Wonder Full lowmuse · low reasoningRank 1 of 16

72.495% range 60.4–83.315.3 points higher

A directional read: their 95% score ranges overlap.

Cost / task

Haiku 5.5 max$3.85
Muse Wonder Full lownot recorded

Agent time / task

Haiku 5.5 max58.4 min
Muse Wonder Full low21.6 min2.7× faster

Quality

Head-to-head matchups

Haiku 5.5 max won4

Tied35 undecided

Muse Wonder Full low won12

Muse Wonder Full low’s win share 69%, 95% range 49–87%Ties are within judge noise.

Task by task

Haiku 5.5 max solved 2 tasks that Muse Wonder Full low didn’t, and Muse Wonder Full low solved 4 that Haiku 5.5 max didn’t. Both solved 8; neither solved 5.

Haiku 5.5 max only 2

  • stet-6f84e978Equivalent to the merged fix
  • stet-commit-342d0ac0Equivalent to the merged fix

Muse Wonder Full low only 4

  • stet-232b50baPassed tests
  • stet-66762b4cEquivalent to the merged fix
  • stet-43493c52Passed tests
  • stet-commit-e928166fEquivalent 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. 5 of the 24 tasks are left out because one of the two has no scored result on them.

All 19 compared tasks
Task by task
TaskHaiku 5.5 maxMuse Wonder Full lowSolved by
stet-3169aefaPassed testsPassed testsBoth
stet-89dfbc27Passed testsPassed testsBoth
stet-b28f4fe7Passed testsPassed testsBoth
stet-232b50baFailedPassed testsMuse Wonder Full low only
stet-5276aa3fPassed testsPassed testsBoth
stet-commit-bbbbae09Passed testsPassed testsBoth
stet-66762b4cFailedEquivalent to the merged fixMuse Wonder Full low only
stet-15439c21Passed testsPassed testsBoth
stet-commit-5d766ddeEquivalent to the merged fixEquivalent to the merged fixBoth
stet-43493c52FailedPassed testsMuse Wonder Full low only
stet-6f84e978Equivalent to the merged fixFailedHaiku 5.5 max only
stet-2450ca2dPassed testsPassed testsBoth
stet-commit-342d0ac0Equivalent to the merged fixFailedHaiku 5.5 max only
stet-commit-5e075641FailedFailedNeither
stet-commit-a8716b88FailedFailedNeither
stet-commit-e928166fFailedEquivalent to the merged fixMuse Wonder Full low only
stet-commit-30506f8eFailedFailedNeither
stet-commit-d2ab0c25FailedFailedNeither
stet-commit-e41c2e2dFailedFailedNeither

Side by side

Side by side
MetricHaiku 5.5 maxMuse Wonder Full low
Harnessclaude-codemuse
Reasoning effortmaxlow
Rank7 of 161 of 16
Stet score57.195% range 45.9–67.672.495% range 60.4–83.3
Solved12/249 passed, 3 judged equivalent12/249 passed, 3 judged equivalent
Cost / task$3.85not recorded
Agent time / task58.4 min21.6 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