Skip to the comparison

DeepSeek V4.1 Flash (10/17) max vs GLM 5.3 Flash high

GLM 5.3 Flash high leads on speed; DeepSeek V4.1 Flash (10/17) max on cost; no clear quality difference.

Quality
Even
No clear difference
1–4 head to head, 15 tied
Speed
1.4× faster
GLM 5.3 Flash high
26.6 min vs 37.2 min per task
Cost
1.6× cheaper
DeepSeek V4.1 Flash (10/17) max
$0.28 vs $0.45 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

24 tasksData from

Stet score

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

48.395% range 42.9–53.41.2 points higher

GLM 5.3 Flash highhigh reasoningRank 13 of 18

47.195% range 39.3–55.3

A directional read: their 95% score ranges overlap.

Quality

Head-to-head matchups

DeepSeek V4.1 Flash (10/17) max won1

Tied15

4 undecided

GLM 5.3 Flash high won4

GLM 5.3 Flash high’s win share 56%, 95% range 45–67%Ties are within judge noise.

Task by task

DeepSeek V4.1 Flash (10/17) max solved 1 task that GLM 5.3 Flash high didn’t, and GLM 5.3 Flash high solved 2 that DeepSeek V4.1 Flash (10/17) max didn’t. Both solved 7; neither solved 9.

On the 7 tasks both solved, judges preferred GLM 5.3 Flash high’s patch on 1 and called 6 even.

1Only 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

2Only GLM 5.3 Flash high solved

  • 113 changed lines in 4 filesstet-commit-f0caded9Judges preferred GLM 5.3 Flash high’s patch
  • 1,312 changed lines in 9 filesstet-commit-f8ae1177Judges preferred GLM 5.3 Flash high’s patch

7Both solved

  • 6 changed lines in 1 filestet-3169aefa
  • 9 changed lines in 1 filestet-89dfbc27
  • 10 changed lines in 1 filestet-232b50ba
  • 23 changed lines in 2 filesstet-5276aa3f
  • 29 changed lines in 1 filestet-b28f4fe7
  • 84 changed lines in 1 filestet-66762b4c
  • 941 changed lines in 7 filesstet-commit-bbbbae09Judges preferred GLM 5.3 Flash high’s patch

9Neither solved

  • 149 changed lines in 2 filesstet-commit-e928166f
  • 481 changed lines in 3 filesstet-commit-5e075641
  • 552 changed lines in 11 filesstet-commit-60a0e6c2
  • 564 changed lines in 10 filesstet-commit-a8716b88
  • 640 changed lines in 8 filesstet-commit-342d0ac0
  • 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
  • 1,420 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. 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
TaskDeepSeek V4.1 Flash (10/17) maxGLM 5.3 Flash highSolved byBetter patch
stet-3169aefa · 6 changed lines in 1 filePassed tests$0.06 · 15.9 minPassed tests$0.05 · 7.0 minBothEven
stet-89dfbc27 · 9 changed lines in 1 filePassed tests$0.05 · 4.9 minPassed tests$0.04 · 6.6 minBothEven
stet-b28f4fe7 · 29 changed lines in 1 filePassed tests$0.06 · 28.7 minPassed tests$0.04 · 7.2 minBothEven
stet-232b50ba · 10 changed lines in 1 filePassed tests$0.05 · 28.0 minPassed tests$0.04 · 10.7 minBothEven
stet-5276aa3f · 23 changed lines in 2 filesPassed tests$0.02 · 14.4 minPassed tests$0.08 · 12.7 minBothEven
stet-commit-bbbbae09 · 941 changed lines in 7 filesPassed tests$0.65 · 47.7 minPassed tests$0.36 · 30.6 minBothGLM 5.3 Flash high
stet-66762b4c · 84 changed lines in 1 filePassed tests$0.08 · 9.1 minPassed tests$0.06 · 12.6 minBothEven
stet-43493c52 · 4 changed lines in 1 filePassed tests$0.14 · 16.0 minFailed$0.07 · 14.0 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 minPassed tests$0.45 · 20.9 minGLM 5.3 Flash high onlyGLM 5.3 Flash high
stet-commit-f8ae1177 · 1,312 changed lines in 9 filesFailed$0.54 · 75.0 minPassed tests$0.58 · 40.1 minGLM 5.3 Flash high onlyGLM 5.3 Flash high
stet-commit-342d0ac0 · 640 changed lines in 8 filesFailed$0.20 · 38.3 minFailed$0.30 · 37.6 minNeitherEven
stet-commit-60a0e6c2 · 552 changed lines in 11 filesFailed$0.34 · 39.2 minFailed$0.27 · 22.2 minNeitherEven
stet-commit-5e075641 · 481 changed lines in 3 filesFailed$0.46 · 53.1 minFailed$0.32 · 36.2 minNeitherEven
stet-commit-2826765e · 1,420 changed lines in 19 filesFailed$0.56 · 50.2 minFailed$0.36 · 31.5 minNeitherEven
stet-commit-a8716b88 · 564 changed lines in 10 filesFailed$0.30 · 40.2 minFailed$0.40 · 32.7 minNeitherEven
stet-commit-e928166f · 149 changed lines in 2 filesFailed$0.29 · 42.0 minFailed$0.17 · 13.2 minNeitherEven
stet-commit-87814583 · 763 changed lines in 8 filesFailed$0.50 · 62.2 minFailed$1.75 · 57.0 minNeitherEven
stet-commit-d2ab0c25 · 1,236 changed lines in 16 filesFailed$0.71 · 76.4 minFailed$0.61 · 34.5 minNeitherEven
stet-commit-e41c2e2d · 977 changed lines in 5 filesFailed$0.96 · 110.4 minFailed$2.92 · 92.9 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 $0.32 · median $0.29

GLM 5.3 Flash highmean $0.47 · median $0.30

GLM 5.3 Flash high cost less on 12 of 19 tasks; DeepSeek V4.1 Flash (10/17) max on 7.

Agent time per task

DeepSeek V4.1 Flash (10/17) maxmean 40.3 min · median 39.2 min

GLM 5.3 Flash highmean 27.4 min · median 22.2 min

GLM 5.3 Flash high finished faster on 16 of 19 tasks; DeepSeek V4.1 Flash (10/17) max on 3.

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

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

DeepSeek V4.1 Flash (10/17) max solved 1 more, 7 of 7 to 6; GLM 5.3 Flash high cost 1.2× less per task.

GLM 5.3 Flash high was 1.7× faster.

Small fixes
DeepSeek V4.1 Flash (10/17) maxGLM 5.3 Flash high
Solved7/76/7
Cost / task$0.07$0.05
Agent time / task16.7 min10.1 min

Large, cross-cutting changes

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

GLM 5.3 Flash high solved 2 more, 3 of 12 to 1; DeepSeek V4.1 Flash (10/17) max cost 1.5× less per task.

GLM 5.3 Flash high was 1.4× faster.

Large, cross-cutting changes
DeepSeek V4.1 Flash (10/17) maxGLM 5.3 Flash high
Solved1/123/12
Cost / task$0.47$0.71
Agent time / task54.1 min37.4 min

Side by side

Side by side
MetricDeepSeek V4.1 Flash (10/17) maxGLM 5.3 Flash high
Harnesscodex—
Reasoning effortmaxhigh
Rank11 of 1813 of 18
Stet score48.395% range 42.9–53.447.195% range 39.3–55.3
Solved10/249 passed, 1 judged equivalent10/2410 passed, 0 judged equivalent
Cost / task$0.28$0.45from 20/24 tasks
Agent time / task37.2 min26.6 minfrom 20/24 tasks

Questions

Which is better for coding, DeepSeek V4.1 Flash (10/17) max or GLM 5.3 Flash high?
No clear quality difference: GLM 5.3 Flash high won 4, DeepSeek V4.1 Flash (10/17) max won 1, 15 tied, 4 undecided; DeepSeek V4.1 Flash (10/17) max leads on cost: 1.6× cheaper; GLM 5.3 Flash high leads on agent time: 1.4× faster. Measured on 24 merged changes from Stet-AI/stet.
How were DeepSeek V4.1 Flash (10/17) max and GLM 5.3 Flash high 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