Skip to the comparison

DeepSeek V4.1 Flash (10/17) max vs GPT 6 Luna low

GPT 6 Luna low leads on speed and cost; DeepSeek V4.1 Flash (10/17) max has a slight edge on quality.

Quality
+7.6 pts
DeepSeek V4.1 Flash (10/17) max
Slight edge
4–1 head to head, 15 tied
Speed
5.4× faster
GPT 6 Luna low
6.9 min vs 37.2 min per task
Cost
5.3× cheaper
GPT 6 Luna low
$0.05 vs $0.28 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 GPT 6 Luna: all effort pairings

24 tasksData from

Stet score

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

48.395% range 42.9–53.47.6 points higher

GPT 6 Luna lowlow reasoningRank 18 of 18

40.795% range 32.0–49.2

A directional read: their 95% score ranges overlap.

Quality

Head-to-head matchups

DeepSeek V4.1 Flash (10/17) max won4

Tied15

4 undecided

GPT 6 Luna low won1

DeepSeek V4.1 Flash (10/17) max’s win share 57%, 95% range 46–68%Ties are within judge noise.

Task by task

DeepSeek V4.1 Flash (10/17) max solved 4 tasks that GPT 6 Luna low didn’t, and GPT 6 Luna low solved 0 that DeepSeek V4.1 Flash (10/17) max didn’t. Both solved 4; neither solved 10.

On the 4 tasks both solved, judges called every patch even.

4Only DeepSeek V4.1 Flash (10/17) max solved

  • 2 changed lines in 1 filestet-2450ca2dJudges preferred DeepSeek V4.1 Flash (10/17) max’s patch
  • 4 changed lines in 1 filestet-43493c52Judges preferred DeepSeek V4.1 Flash (10/17) max’s patch
  • 23 changed lines in 2 filesstet-5276aa3fJudges 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

0Only GPT 6 Luna low solved

None

4Both solved

  • 6 changed lines in 1 filestet-3169aefa
  • 9 changed lines in 1 filestet-89dfbc27
  • 10 changed lines in 1 filestet-232b50ba
  • 29 changed lines in 1 filestet-b28f4fe7

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
  • 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. 6 of the 24 tasks are left out because one of the two has no scored result on them.

All 18 compared tasks
Task by task
TaskDeepSeek V4.1 Flash (10/17) maxGPT 6 Luna lowSolved byBetter patch
stet-3169aefa · 6 changed lines in 1 filePassed tests$0.06 · 15.9 minPassed tests$0.01 · 1.7 minBothEven
stet-89dfbc27 · 9 changed lines in 1 filePassed tests$0.05 · 4.9 minPassed tests$0.01 · 3.3 minBothEven
stet-b28f4fe7 · 29 changed lines in 1 filePassed tests$0.06 · 28.7 minPassed tests$0.01 · 1.6 minBothEven
stet-232b50ba · 10 changed lines in 1 filePassed tests$0.05 · 28.0 minPassed tests$0.01 · 1.8 minBothEven
stet-5276aa3f · 23 changed lines in 2 filesPassed tests$0.02 · 14.4 minFailed$0.01 · 2.6 minDeepSeek V4.1 Flash (10/17) max onlyDeepSeek V4.1 Flash (10/17) max
stet-66762b4c · 84 changed lines in 1 filePassed tests$0.08 · 9.1 minFailed$0.01 · 1.5 minDeepSeek V4.1 Flash (10/17) max onlyDeepSeek V4.1 Flash (10/17) max
stet-43493c52 · 4 changed lines in 1 filePassed tests$0.14 · 16.0 minFailed$0.01 · 1.7 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$0.03 · 4.5 minNeitherEven
stet-2450ca2d · 2 changed lines in 1 filePassed tests$0.07 · 10.1 minFailed$0.01 · 1.1 minDeepSeek V4.1 Flash (10/17) max onlyDeepSeek V4.1 Flash (10/17) max
stet-commit-342d0ac0 · 640 changed lines in 8 filesFailed$0.20 · 38.3 minFailed$0.31 · 40.1 minNeitherEven
stet-commit-5e075641 · 481 changed lines in 3 filesFailed$0.46 · 53.1 minFailed$0.01 · 1.8 minNeitherEven
stet-commit-2826765e · 1,420 changed lines in 19 filesFailed$0.56 · 50.2 minFailed$0.02 · 4.2 minNeitherEven
stet-commit-a8716b88 · 564 changed lines in 10 filesFailed$0.30 · 40.2 minFailed$0.21 · 27.1 minNeitherEven
stet-commit-e928166f · 149 changed lines in 2 filesFailed$0.29 · 42.0 minFailed$0.06 · 3.1 minNeitherEven
stet-commit-30506f8e · 476 changed lines in 17 filesFailed$0.38 · 48.8 minFailed$0.23 · 38.4 minNeitherEven
stet-commit-87814583 · 763 changed lines in 8 filesFailed$0.50 · 62.2 minFailed$0.02 · 1.0 minNeitherEven
stet-commit-d2ab0c25 · 1,236 changed lines in 16 filesFailed$0.71 · 76.4 minFailed$0.10 · 7.2 minNeitherEven
stet-commit-e41c2e2d · 977 changed lines in 5 filesFailed$0.96 · 110.4 minFailed$0.09 · 12.1 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 $0.28 · median $0.17

GPT 6 Luna lowmean $0.07 · median $0.02

GPT 6 Luna low cost less on 17 of 18 tasks; DeepSeek V4.1 Flash (10/17) max on 1.

Agent time per task

DeepSeek V4.1 Flash (10/17) maxmean 36.8 min · median 33.5 min

GPT 6 Luna lowmean 8.6 min · median 2.8 min

GPT 6 Luna low finished faster on 17 of 18 tasks; DeepSeek V4.1 Flash (10/17) max on 1.

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 4 more, 8 of 8 to 4; GPT 6 Luna low cost 5.9× less per task.

GPT 6 Luna low was 8.3× faster.

Small fixes
DeepSeek V4.1 Flash (10/17) maxGPT 6 Luna low
Solved8/84/8
Cost / task$0.07$0.01
Agent time / task15.9 min1.9 min

Large, cross-cutting changes

Cheaper here without solving fewer: GPT 6 Luna low

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

GPT 6 Luna low solved as many, 0 of 10, at 4.1× lower cost per task.

GPT 6 Luna low was 3.8× faster.

Large, cross-cutting changes
DeepSeek V4.1 Flash (10/17) maxGPT 6 Luna low
Solved0/100/10
Cost / task$0.44$0.11
Agent time / task53.6 min13.9 min

Side by side

Side by side
MetricDeepSeek V4.1 Flash (10/17) maxGPT 6 Luna low
Harnesscodex—
Reasoning effortmaxlow
Rank11 of 1818 of 18
Stet score48.395% range 42.9–53.440.795% range 32.0–49.2
Solved10/249 passed, 1 judged equivalent5/245 passed, 0 judged equivalent
Cost / task$0.28$0.05
Agent time / task37.2 min6.9 min

Questions

Which is better for coding, DeepSeek V4.1 Flash (10/17) max or GPT 6 Luna low?
DeepSeek V4.1 Flash (10/17) max has a slight quality edge, 4–1 head to head with 15 tied and 4 undecided; GPT 6 Luna low leads on cost and agent time: 5.3× cheaper and 5.4× faster. Measured on 24 merged changes from Stet-AI/stet.
How were DeepSeek V4.1 Flash (10/17) max and GPT 6 Luna low 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