Skip to the comparison

DeepSeek V4.1 Flash (10/17) max vs Haiku 5.5 max

DeepSeek V4.1 Flash (10/17) max leads on speed and cost; no clear quality difference.

Quality
Even
No clear difference
3–4 head to head, 16 tied
Speed
1.6× faster
DeepSeek V4.1 Flash (10/17) max
37.2 min vs 58.4 min per task
Cost
2.8× cheaper
DeepSeek V4.1 Flash (10/17) max
$0.28 vs $0.78 per task

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

DeepSeek V4.1 Flash (10/17) vs Haiku 5.5: all effort pairings

24 tasksData from

Stet score

DeepSeek V4.1 Flash (10/17) maxcodex · max reasoningRank 11 of 18

48.395% range 42.9–53.4

Haiku 5.5 maxmax reasoningRank 10 of 18

48.895% range 38.6–58.70.5 points higher

A directional read: their 95% score ranges overlap.

Quality

Head-to-head matchups

DeepSeek V4.1 Flash (10/17) max won3

Tied16

1 undecided

Haiku 5.5 max won4

Haiku 5.5 max’s win share 54%, 95% range 43–65%Ties are within judge noise.

Task by task

DeepSeek V4.1 Flash (10/17) max solved 3 tasks that Haiku 5.5 max didn’t, and Haiku 5.5 max solved 1 that DeepSeek V4.1 Flash (10/17) max didn’t. Both solved 7; neither solved 10.

On the 7 tasks both solved, judges preferred Haiku 5.5 max’s patch on 1 and called 6 even.

3Only DeepSeek V4.1 Flash (10/17) max solved

  • 4 changed lines in 1 filestet-43493c52Judges preferred DeepSeek V4.1 Flash (10/17) max’s patch
  • 10 changed lines in 1 filestet-232b50baJudges preferred DeepSeek V4.1 Flash (10/17) max’s patch
  • 84 changed lines in 1 filestet-66762b4cJudges preferred DeepSeek V4.1 Flash (10/17) max’s patch

1Only Haiku 5.5 max solved

  • 640 changed lines in 8 filesstet-commit-342d0ac0Judges preferred Haiku 5.5 max’s patch

7Both solved

  • 2 changed lines in 1 filestet-2450ca2d
  • 6 changed lines in 1 filestet-3169aefa
  • 9 changed lines in 1 filestet-89dfbc27
  • 23 changed lines in 2 filesstet-5276aa3f
  • 29 changed lines in 1 filestet-b28f4fe7
  • 218 changed lines in 2 filesstet-commit-5d766dde
  • 941 changed lines in 7 filesstet-commit-bbbbae09Judges preferred Haiku 5.5 max’s patch

10Neither solved

  • 113 changed lines in 4 filesstet-commit-f0caded9
  • 149 changed lines in 2 filesstet-commit-e928166f
  • 476 changed lines in 17 filesstet-commit-30506f8e
  • 481 changed lines in 3 filesstet-commit-5e075641
  • 564 changed lines in 10 filesstet-commit-a8716b88
  • 763 changed lines in 8 filesstet-commit-87814583
  • 977 changed lines in 5 filesstet-commit-e41c2e2d
  • 1,236 changed lines in 16 filesstet-commit-d2ab0c25
  • 1,312 changed lines in 9 filesstet-commit-f8ae1177
  • 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. 3 of the 24 tasks are left out because one of the two has no scored result on them.

All 21 compared tasks
Task by task
TaskDeepSeek V4.1 Flash (10/17) maxHaiku 5.5 maxSolved byBetter patch
stet-3169aefa · 6 changed lines in 1 filePassed tests$0.06 · 15.9 minPassed tests$0.20 · 38.5 minBothEven
stet-89dfbc27 · 9 changed lines in 1 filePassed tests$0.05 · 4.9 minPassed tests$0.06 · 6.3 minBothEven
stet-b28f4fe7 · 29 changed lines in 1 filePassed tests$0.06 · 28.7 minPassed tests$0.24 · 22.2 minBothEven
stet-232b50ba · 10 changed lines in 1 filePassed tests$0.05 · 28.0 minFailed$0.69 · 45.5 minDeepSeek V4.1 Flash (10/17) max onlyDeepSeek V4.1 Flash (10/17) max
stet-5276aa3f · 23 changed lines in 2 filesPassed tests$0.02 · 14.4 minPassed tests$0.09 · 25.3 minBothEven
stet-commit-bbbbae09 · 941 changed lines in 7 filesPassed tests$0.65 · 47.7 minPassed tests$0.73 · 47.8 minBothHaiku 5.5 max
stet-66762b4c · 84 changed lines in 1 filePassed tests$0.08 · 9.1 minFailed$0.15 · 39.4 minDeepSeek V4.1 Flash (10/17) max onlyDeepSeek V4.1 Flash (10/17) max
stet-commit-5d766dde · 218 changed lines in 2 filesEquivalent to the merged fix$0.09 · 18.5 minEquivalent to the merged fix$0.37 · 31.7 minBothEven
stet-43493c52 · 4 changed lines in 1 filePassed tests$0.14 · 16.0 minFailed$0.24 · 71.0 minDeepSeek V4.1 Flash (10/17) max onlyDeepSeek V4.1 Flash (10/17) max
stet-commit-f0caded9 · 113 changed lines in 4 filesFailed$0.09 · 14.6 minFailed$1.91 · 153.7 minNeitherEven
stet-commit-f8ae1177 · 1,312 changed lines in 9 filesFailed$0.54 · 75.0 minFailed$2.49 · 126.3 minNeitherEven
stet-2450ca2d · 2 changed lines in 1 filePassed tests$0.07 · 10.1 minPassed tests$0.35 · 56.7 minBothEven
stet-commit-342d0ac0 · 640 changed lines in 8 filesFailed$0.20 · 38.3 minEquivalent to the merged fix$1.59 · 82.3 minHaiku 5.5 max onlyHaiku 5.5 max
stet-commit-5e075641 · 481 changed lines in 3 filesFailed$0.46 · 53.1 minFailed$0.79 · 59.0 minNeitherEven
stet-commit-2826765e · 1,420 changed lines in 19 filesFailed$0.56 · 50.2 minFailed$0.79 · 78.2 minNeitherEven
stet-commit-a8716b88 · 564 changed lines in 10 filesFailed$0.30 · 40.2 minFailed$0.96 · 95.4 minNeitherEven
stet-commit-e928166f · 149 changed lines in 2 filesFailed$0.29 · 42.0 minFailed$0.35 · 35.6 minNeitherEven
stet-commit-30506f8e · 476 changed lines in 17 filesFailed$0.38 · 48.8 minFailed$1.67 · 100.0 minNeitherEven
stet-commit-87814583 · 763 changed lines in 8 filesFailed$0.50 · 62.2 minFailed$0.87 · 61.9 minNeitherEven
stet-commit-d2ab0c25 · 1,236 changed lines in 16 filesFailed$0.71 · 76.4 minFailed$2.15 · 92.8 minNeitherEven
stet-commit-e41c2e2d · 977 changed lines in 5 filesFailed$0.96 · 110.4 minFailed$0.59 · 44.0 minNeitherEven

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

DeepSeek V4.1 Flash (10/17) maxmean $0.30 · median $0.20

Haiku 5.5 maxmean $0.82 · median $0.69

DeepSeek V4.1 Flash (10/17) max cost less on 20 of 21 tasks; Haiku 5.5 max on 1.

Agent time per task

DeepSeek V4.1 Flash (10/17) maxmean 38.3 min · median 38.3 min

Haiku 5.5 maxmean 62.6 min · median 56.7 min

DeepSeek V4.1 Flash (10/17) max finished faster on 17 of 21 tasks; Haiku 5.5 max on 4.

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: DeepSeek V4.1 Flash (10/17) max

10 tasks · 2–84 changed lines in 1–2 files

DeepSeek V4.1 Flash (10/17) max solved more, 8 of 8 to 5, at 3.8× lower cost per task.

DeepSeek V4.1 Flash (10/17) max was 2.4× faster.

Small fixes
DeepSeek V4.1 Flash (10/17) maxHaiku 5.5 max
Solved8/85/8
Cost / task$0.07$0.25
Agent time / task15.9 min38.1 min

Large, cross-cutting changes

14 tasks · 113–1,420 changed lines in up to 19 files

Haiku 5.5 max solved 1 more, 3 of 13 to 2; DeepSeek V4.1 Flash (10/17) max cost 2.7× less per task.

DeepSeek V4.1 Flash (10/17) max was 1.5× faster.

Large, cross-cutting changes
DeepSeek V4.1 Flash (10/17) maxHaiku 5.5 max
Solved2/133/13
Cost / task$0.44$1.17
Agent time / task52.1 min77.6 min

Side by side

Side by side
MetricDeepSeek V4.1 Flash (10/17) maxHaiku 5.5 max
Harnesscodex—
Reasoning effortmaxmax
Rank11 of 1810 of 18
Stet score48.395% range 42.9–53.448.895% range 38.6–58.7
Solved10/249 passed, 1 judged equivalent10/247 passed, 3 judged equivalent
Cost / task$0.28$0.78
Agent time / task37.2 min58.4 min

Questions

Which is better for coding, DeepSeek V4.1 Flash (10/17) max or Haiku 5.5 max?
No clear quality difference: Haiku 5.5 max won 4, DeepSeek V4.1 Flash (10/17) max won 3, 16 tied, 1 undecided; DeepSeek V4.1 Flash (10/17) max leads on cost and agent time: 2.8× cheaper and 1.6× faster. Measured on 24 merged changes from Stet-AI/stet.
How were DeepSeek V4.1 Flash (10/17) max and Haiku 5.5 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.

Get started