Muse Spark 1.3 high vs Muse Wonder Full low

Muse Wonder Full low leads on quality: won 16, tied 3, lost 1, 4 undecided head to head; Muse Spark 1.3 high leads on cost and agent time: 28.4× cheaper and 1.6× faster.

24 tasksData from October 29, 2026

Stet score

Muse Spark 1.3 highmuse · high reasoningRank 14 of 16

31.995% range 23.5–40.6

Muse Wonder Full lowmuse · low reasoningRank 1 of 16

70.495% range 58.6–81.238.5 points higher

Other setups

GPT 5.6 Luna max

70.3

SWE-2 Max high

64.3

GPT 6.1 Sol medium

62.5

Opus 5 medium

62.3

Grok 4.7 high

60.7

Pareto 26.9 medium

57.1

Haiku 5.5 max

55.5

GPT 6 Sol medium

55.4

GPT 6 Luna max

47.4

DeepSeek V4.1 Flash max

45.9

Opus 4.8 medium

39.2

Haiku 5.5 low

38.9

GLM 5.3 Flash high

29.0

GPT 6 Luna low

19.9

Their 95% score ranges don’t overlap.

Cost / task

Muse Spark 1.3 high$0.1028.4× cheaper

Muse Wonder Full low$2.85

Agent time / task

Muse Spark 1.3 high13.2 min1.6× faster

Muse Wonder Full low21.6 min

Quality

Head-to-head matchups

Muse Spark 1.3 high won1

Tied34 undecided

Muse Wonder Full low won16

Muse Wonder Full low’s win share 87%, 95% range 74–96%Ties are within judge noise.

Task by task

Muse Spark 1.3 high solved 0 tasks that Muse Wonder Full low didn’t, and Muse Wonder Full low solved 2 that Muse Spark 1.3 high didn’t. Both solved 10; neither solved 8.

Muse Spark 1.3 high only 0

Muse Wonder Full low only 2

stet-15439c21Passed 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. 4 of the 24 tasks are left out because one of the two has no scored result on them.

All 20 compared tasks

Task by task
Task	Muse Spark 1.3 high	Muse Wonder Full low	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-66762b4c`	Passed tests	Equivalent to the merged fix	Both
`stet-15439c21`	Failed	Passed tests	Muse Wonder Full 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-2450ca2d`	Equivalent to the merged fix	Passed tests	Both
`stet-commit-342d0ac0`	Failed	Failed	Neither
`stet-commit-60a0e6c2`	Failed	Failed	Neither
`stet-commit-5e075641`	Failed	Failed	Neither
`stet-commit-a8716b88`	Failed	Failed	Neither
`stet-commit-e928166f`	Failed	Equivalent to the merged fix	Muse Wonder Full low only
`stet-commit-30506f8e`	Failed	Failed	Neither
`stet-commit-d2ab0c25`	Failed	Failed	Neither
`stet-commit-e41c2e2d`	Failed	Failed	Neither

Side by side

Side by side
Metric	Muse Spark 1.3 high	Muse Wonder Full low
Harness	muse	muse
Reasoning effort	high	low
Rank	14 of 16	1 of 16
Stet score	31.995% range 23.5–40.6	70.495% range 58.6–81.2
Solved	10/248 passed, 2 judged equivalent	12/249 passed, 3 judged equivalent
Cost / task	$0.10	$2.85
Agent time / task	13.2 min	21.6 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 October 29, 2026.
Both setups come from the same leaderboard run of 16 setups: bmk_d4ba310fdf50db4ccb2092e3.

See all 16 setups on the leaderboard How Stet measures