Skip to the comparison
STET
Join the waitlist

DeepSeek V4.1 Flash max vs Muse Wonder Full low

No clear quality winner: Muse Wonder Full low won 12, DeepSeek V4.1 Flash max won 4, 4 tied, 4 undecided; DeepSeek V4.1 Flash max leads on cost: 5.8× cheaper; Muse Wonder Full low leads on agent time: 2.3× faster.

24 tasksData from

Stet score

DeepSeek V4.1 Flash maxdeepseek-harness · max reasoningRank 11 of 16

45.995% range 35.5–56.1

Muse Wonder Full lowmuse · low reasoningRank 1 of 16

70.495% range 58.6–81.224.5 points higher

Their 95% score ranges don’t overlap.

Cost / task

DeepSeek V4.1 Flash max$0.495.8× cheaperfrom 23/24 tasks
Muse Wonder Full low$2.85

Agent time / task

DeepSeek V4.1 Flash max49.3 min
Muse Wonder Full low21.6 min2.3× faster

Quality

Head-to-head matchups

DeepSeek V4.1 Flash max won4

Tied44 undecided

Muse Wonder Full low won12

Muse Wonder Full low’s win share 69%, 95% range 51–85%Ties are within judge noise.

Task by task

DeepSeek V4.1 Flash max solved 1 task that Muse Wonder Full low didn’t, and Muse Wonder Full low solved 2 that DeepSeek V4.1 Flash max didn’t. Both solved 10; neither solved 7.

DeepSeek V4.1 Flash max only 1

  • stet-commit-342d0ac0Equivalent to the merged fix

Muse Wonder Full low only 2

  • stet-2450ca2dPassed 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
TaskDeepSeek V4.1 Flash maxMuse Wonder Full lowSolved by
stet-3169aefaPassed testsPassed testsBoth
stet-89dfbc27Passed testsPassed testsBoth
stet-b28f4fe7Passed testsPassed testsBoth
stet-232b50baPassed testsPassed testsBoth
stet-5276aa3fPassed testsPassed testsBoth
stet-commit-bbbbae09Passed testsPassed testsBoth
stet-66762b4cPassed testsEquivalent to the merged fixBoth
stet-15439c21Passed testsPassed testsBoth
stet-commit-5d766ddePassed testsEquivalent to the merged fixBoth
stet-43493c52Passed testsPassed testsBoth
stet-6f84e978FailedFailedNeither
stet-2450ca2dFailedPassed testsMuse Wonder Full low only
stet-commit-342d0ac0Equivalent to the merged fixFailedDeepSeek V4.1 Flash max only
stet-commit-60a0e6c2FailedFailedNeither
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
MetricDeepSeek V4.1 Flash maxMuse Wonder Full low
Harnessdeepseek-harnessmuse
Reasoning effortmaxlow
Rank11 of 161 of 16
Stet score45.995% range 35.5–56.170.495% range 58.6–81.2
Solved12/2411 passed, 1 judged equivalent12/249 passed, 3 judged equivalent
Cost / task$0.49from 23/24 tasks$2.85
Agent time / task49.3 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