Skip to the comparison
STET
Join the waitlist

GPT 6 Luna max vs Pareto 26.9 medium

No clear quality winner: Pareto 26.9 medium won 9, GPT 6 Luna max won 8, 7 tied; GPT 6 Luna max leads on cost: 33.3× cheaper; Pareto 26.9 medium leads on agent time: 1.5× faster.

24 tasksData from

Stet score

GPT 6 Luna maxcodex · max reasoningRank 10 of 16

47.495% range 38.0–56.4

Pareto 26.9 mediumclaude-code · medium reasoningRank 7 of 16

57.195% range 47.0–66.79.7 points higher

A directional read: their 95% score ranges overlap.

Cost / task

GPT 6 Luna max$0.3733.3× cheaper
Pareto 26.9 medium$12.47

Agent time / task

GPT 6 Luna max59.7 min
Pareto 26.9 medium39.2 min1.5× faster

Quality

Head-to-head matchups

GPT 6 Luna max won8

Tied7

Pareto 26.9 medium won9

Pareto 26.9 medium’s win share 55%, 95% range 39–71%Ties are within judge noise.

Task by task

GPT 6 Luna max solved 2 tasks that Pareto 26.9 medium didn’t, and Pareto 26.9 medium solved 3 that GPT 6 Luna max didn’t. Both solved 10; neither solved 9.

GPT 6 Luna max only 2

  • stet-commit-5d766ddeEquivalent to the merged fix
  • stet-commit-342d0ac0Equivalent to the merged fix

Pareto 26.9 medium only 3

  • stet-15439c21Passed tests
  • stet-6f84e978Passed tests
  • stet-2450ca2dPassed tests

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 6 Luna maxPareto 26.9 mediumSolved by
stet-3169aefaPassed testsPassed testsBoth
stet-89dfbc27Passed testsPassed testsBoth
stet-b28f4fe7Passed testsPassed testsBoth
stet-232b50baPassed testsPassed testsBoth
stet-5276aa3fPassed testsPassed testsBoth
stet-commit-bbbbae09Passed testsPassed testsBoth
stet-66762b4cEquivalent to the merged fixPassed testsBoth
stet-15439c21FailedPassed testsPareto 26.9 medium only
stet-commit-5d766ddeEquivalent to the merged fixFailedGPT 6 Luna max only
stet-43493c52Passed testsPassed testsBoth
stet-commit-f0caded9Equivalent to the merged fixEquivalent to the merged fixBoth
stet-6f84e978FailedPassed testsPareto 26.9 medium only
stet-2450ca2dFailedPassed testsPareto 26.9 medium only
stet-commit-342d0ac0Equivalent to the merged fixFailedGPT 6 Luna max only
stet-commit-f8ae1177Passed testsPassed testsBoth
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 6 Luna maxPareto 26.9 medium
Harnesscodexclaude-code
Reasoning effortmaxmedium
Rank10 of 167 of 16
Stet score47.495% range 38.0–56.457.195% range 47.0–66.7
Solved12/248 passed, 4 judged equivalent13/2412 passed, 1 judged equivalent
Cost / task$0.37$12.47
Agent time / task59.7 min39.2 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 16 setups: bmk_d4ba310fdf50db4ccb2092e3.

See all 16 setups on the leaderboardHow Stet measures