DeepSeek V4.1 Flash (10/17) maxcodex · max reasoningRank 11 of 18
48.395% range 42.9–53.44.9 points higher
GPT 5.6 Luna lowcodex · low reasoningRank 17 of 18
43.495% range 36.6–49.9
Other setups
SWE-2 Max high
SWE-2 Max high
63.7
Opus 5 medium
Opus 5 medium
61.2
Muse Wonder Full low
Muse Wonder Full low
56.5
GPT 6.1 Sol medium
GPT 6.1 Sol medium
54.5
GPT 6 Sol medium
GPT 6 Sol medium
53.2
Grok 4.7 high
Grok 4.7 high
52.6
Pareto 26.9 medium
Pareto 26.9 medium
52.2
DeepSeek V4.1 Flash max
DeepSeek V4.1 Flash max
50.9
Opus 4.8 medium
Opus 4.8 medium
48.9
Haiku 5.5 max
Haiku 5.5 max
48.8
Muse Spark 1.3 high
Muse Spark 1.3 high
47.5
GLM 5.3 Flash high
GLM 5.3 Flash high
47.1
GPT 5.6 Luna max
GPT 5.6 Luna max
46.7
GPT 6 Luna max
GPT 6 Luna max
45.2
Haiku 5.5 low
Haiku 5.5 low
44.8
GPT 6 Luna low
GPT 6 Luna low
40.7
304050607080even with the field
A directional read: their 95% score ranges overlap.
Quality
Head-to-head matchups
DeepSeek V4.1 Flash (10/17) max won3
Tied20
GPT 5.6 Luna low won1
DeepSeek V4.1 Flash (10/17) max’s win share 55%, 95% range 48–63%Ties are within judge noise.
Task by task
DeepSeek V4.1 Flash (10/17) max solved 2 tasks that GPT 5.6 Luna low didn’t, and GPT 5.6 Luna low solved 1 that DeepSeek V4.1 Flash (10/17) max didn’t. Both solved 8; neither solved 11.
On the 8 tasks both solved, judges preferred DeepSeek V4.1 Flash (10/17) max’s patch on 1 and called 7 even.
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. 2 of the 24 tasks are left out because one of the two has no scored result on them.
All 22 compared tasks
Task by task
Task
DeepSeek V4.1 Flash (10/17) max
GPT 5.6 Luna low
Solved by
Better patch
stet-3169aefa · 6 changed lines in 1 file
Passed tests$0.06 · 15.9 min
Passed tests$0.02 · 4.9 min
Both
Even
stet-89dfbc27 · 9 changed lines in 1 file
Passed tests$0.05 · 4.9 min
Passed tests$0.04 · 6.5 min
Both
Even
stet-b28f4fe7 · 29 changed lines in 1 file
Passed tests$0.06 · 28.7 min
Passed tests$0.03 · 2.6 min
Both
Even
stet-232b50ba · 10 changed lines in 1 file
Passed tests$0.05 · 28.0 min
Passed tests$0.04 · 14.5 min
Both
Even
stet-5276aa3f · 23 changed lines in 2 files
Passed tests$0.02 · 14.4 min
Passed tests$0.05 · 13.4 min
Both
Even
stet-commit-bbbbae09 · 941 changed lines in 7 files
Passed tests$0.65 · 47.7 min
Failed$0.04 · 6.6 min
DeepSeek V4.1 Flash (10/17) max only
DeepSeek V4.1 Flash (10/17) max
stet-66762b4c · 84 changed lines in 1 file
Passed tests$0.08 · 9.1 min
Equivalent to the merged fix$0.02 · 3.7 min
Both
DeepSeek V4.1 Flash (10/17) max
stet-commit-5d766dde · 218 changed lines in 2 files
Equivalent to the merged fix$0.09 · 18.5 min
Equivalent to the merged fix$0.05 · 10.7 min
Both
Even
stet-43493c52 · 4 changed lines in 1 file
Passed tests$0.14 · 16.0 min
Passed tests$0.03 · 4.0 min
Both
Even
stet-commit-f0caded9 · 113 changed lines in 4 files
Failed$0.09 · 14.6 min
Equivalent to the merged fix$0.04 · 2.9 min
GPT 5.6 Luna low only
Even
stet-commit-f8ae1177 · 1,312 changed lines in 9 files
Failed$0.54 · 75.0 min
Failed$0.05 · 6.7 min
Neither
Even
stet-2450ca2d · 2 changed lines in 1 file
Passed tests$0.07 · 10.1 min
Failed$0.02 · 4.2 min
DeepSeek V4.1 Flash (10/17) max only
DeepSeek V4.1 Flash (10/17) max
stet-commit-342d0ac0 · 640 changed lines in 8 files
Failed$0.20 · 38.3 min
Failed$0.12 · 12.4 min
Neither
Even
stet-commit-60a0e6c2 · 552 changed lines in 11 files
Failed$0.34 · 39.2 min
Failed$0.04 · 2.6 min
Neither
Even
stet-commit-5e075641 · 481 changed lines in 3 files
Failed$0.46 · 53.1 min
Failed$0.07 · 5.7 min
Neither
Even
stet-commit-2826765e · 1,420 changed lines in 19 files
Failed$0.56 · 50.2 min
Failed$0.04 · 7.2 min
Neither
Even
stet-commit-a8716b88 · 564 changed lines in 10 files
Failed$0.30 · 40.2 min
Failed$0.10 · 5.8 min
Neither
Even
stet-commit-e928166f · 149 changed lines in 2 files
Failed$0.29 · 42.0 min
Failed$0.06 · 3.4 min
Neither
Even
stet-commit-30506f8e · 476 changed lines in 17 files
Failed$0.38 · 48.8 min
Failed$0.12 · 10.1 min
Neither
Even
stet-commit-87814583 · 763 changed lines in 8 files
Failed$0.50 · 62.2 min
Failed$0.03 · 2.7 min
Neither
Even
stet-commit-d2ab0c25 · 1,236 changed lines in 16 files
Failed$0.71 · 76.4 min
Failed$0.05 · 5.0 min
Neither
Even
stet-commit-e41c2e2d · 977 changed lines in 5 files
Failed$0.96 · 110.4 min
Failed$0.10 · 8.3 min
Neither
Even
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 $0.25
GPT 5.6 Luna lowmean $0.05 · median $0.04
$0.01$0.10$1
GPT 5.6 Luna low cost less on 21 of 22 tasks; DeepSeek V4.1 Flash (10/17) max on 1.
Agent time per task
DeepSeek V4.1 Flash (10/17) maxmean 38.3 min · median 38.7 min
GPT 5.6 Luna lowmean 6.5 min · median 5.7 min
1 min10 min100 min1000 min
GPT 5.6 Luna low finished faster on 21 of 22 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 1 more, 8 of 8 to 7; GPT 5.6 Luna low cost 2.1× less per task.
GPT 5.6 Luna low was 2.4× faster.
Small fixes
DeepSeek V4.1 Flash (10/17) max
GPT 5.6 Luna low
Solved
8/8
7/8
Cost / task
$0.07
$0.03
Agent time / task
15.9 min
6.7 min
Large, cross-cutting changes
Cheaper here without solving fewer: GPT 5.6 Luna low
14 tasks · 113–1,420 changed lines in up to 19 files
GPT 5.6 Luna low solved as many, 2 of 14, at 6.6× lower cost per task.
GPT 5.6 Luna low was 8.0× faster.
Large, cross-cutting changes
DeepSeek V4.1 Flash (10/17) max
GPT 5.6 Luna low
Solved
2/14
2/14
Cost / task
$0.43
$0.07
Agent time / task
51.2 min
6.4 min
Side by side
Side by side
Metric
DeepSeek V4.1 Flash (10/17) max
GPT 5.6 Luna low
Harness
codex
codex
Reasoning effort
max
low
Rank
11 of 18
17 of 18
Stet score
48.395% range 42.9–53.4
43.495% range 36.6–49.9
Solved
10/249 passed, 1 judged equivalent
10/247 passed, 3 judged equivalent
Cost / task
$0.28
$0.05
Agent time / task
37.2 min
6.7 min
Questions
Which is better for coding, DeepSeek V4.1 Flash (10/17) max or GPT 5.6 Luna low?
DeepSeek V4.1 Flash (10/17) max has a slight quality edge, 3–1 head to head with 20 tied; GPT 5.6 Luna low leads on cost and agent time: 5.5× cheaper and 5.6× faster. Measured on 24 merged changes from Stet-AI/stet.
How were DeepSeek V4.1 Flash (10/17) max and GPT 5.6 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.