Skip to the comparison
STET
Run it on your repo

GPT 5.6 Luna max vs GPT 6 Luna max

GPT 5.6 Luna max leads on speed; GPT 6 Luna max on cost; quality is too close to call.

Quality
+3.4 pts
GPT 5.6 Luna max
2–0 head to head, 22 tied
Speed
2.1× faster
GPT 5.6 Luna max
28.5 min vs 59.7 min per task
Cost
2.4× cheaper
GPT 6 Luna max
$0.37 vs $0.90 per task

24 tasksData from

Stet score

GPT 5.6 Luna maxmax reasoningRank 9 of 17

49.995% range 44.5–55.63.4 points higher

GPT 6 Luna maxmax reasoningRank 13 of 17

46.595% range 41.1–51.7

A directional read: their 95% score ranges overlap.

Quality

Head-to-head matchups

GPT 5.6 Luna max won2

Tied22

GPT 6 Luna max won0

GPT 5.6 Luna max’s win share 54%, 95% range 50–59%Ties are within judge noise.

Task by task

GPT 5.6 Luna max solved 0 tasks that GPT 6 Luna max didn’t, and GPT 6 Luna max solved 1 that GPT 5.6 Luna max didn’t. Both solved 10; neither solved 13.

stet-commit-342d0ac0Solved by 6 of 17 setups

  • GPT 5.6 Luna maxFailed
  • GPT 6 Luna maxEquivalent 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.

All 24 compared tasks
Task by task
TaskGPT 5.6 Luna maxGPT 6 Luna maxSolved by
stet-232b50baPassed testsPassed testsBoth
stet-3169aefaPassed testsPassed testsBoth
stet-5276aa3fPassed testsPassed testsBoth
stet-89dfbc27Passed testsPassed testsBoth
stet-b28f4fe7Passed testsPassed testsBoth
stet-commit-bbbbae09Passed testsPassed testsBoth
stet-66762b4cEquivalent to the merged fixEquivalent to the merged fixBoth
stet-commit-5d766ddeEquivalent to the merged fixEquivalent to the merged fixBoth
stet-commit-f0caded9Equivalent to the merged fixEquivalent to the merged fixBoth
stet-43493c52Passed testsPassed testsBoth
stet-commit-f8ae1177FailedFailedNeither
stet-15439c21FailedFailedNeither
stet-2450ca2dFailedFailedNeither
stet-commit-342d0ac0FailedEquivalent to the merged fixGPT 6 Luna max only
stet-6f84e978FailedFailedNeither
stet-commit-60a0e6c2FailedFailedNeither
stet-commit-5e075641FailedFailedNeither
stet-commit-2826765eFailedFailedNeither
stet-commit-a8716b88FailedFailedNeither
stet-commit-e928166fFailedFailedNeither
stet-commit-30506f8eFailedFailedNeither
stet-commit-87814583FailedFailedNeither
stet-commit-d2ab0c25FailedFailedNeither
stet-commit-e41c2e2dFailedFailedNeither

Side by side

Side by side
MetricGPT 5.6 Luna maxGPT 6 Luna max
Reasoning effortmaxmax
Rank9 of 1713 of 17
Stet score49.995% range 44.5–55.646.595% range 41.1–51.7
Solved10/247 passed, 3 judged equivalent11/247 passed, 4 judged equivalent
Cost / task$0.90$0.37
Agent time / task28.5 min59.7 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 17 setups: bmk_d4ba310fdf50db4ccb2092e3.

See all 17 setups on the leaderboardHow Stet measures