Skip to the comparison
STET
Join the waitlist

GPT 6.1 Sol medium vs SWE-2 Max high

No clear quality winner: SWE-2 Max high won 10, GPT 6.1 Sol medium won 6, 8 tied; GPT 6.1 Sol medium leads on agent time: 5.8× faster; SWE-2 Max high’s cost wasn’t recorded.

24 tasksData from

Stet score

GPT 6.1 Sol mediumcodex · medium reasoningRank 3 of 15

64.195% range 54.3–73.4

SWE-2 Max highdevin · high reasoningRank 2 of 15

65.195% range 55.2–74.71.0 point higher

A directional read: their 95% score ranges overlap.

Cost / task

GPT 6.1 Sol medium$1.10
SWE-2 Max highnot recorded

Agent time / task

GPT 6.1 Sol medium11.8 min5.8× faster
SWE-2 Max high68.3 min

Quality

Head-to-head matchups

GPT 6.1 Sol medium won6

Tied8

SWE-2 Max high won10

SWE-2 Max high’s win share 57%, 95% range 40–73%Ties are within judge noise.

Task by task

GPT 6.1 Sol medium solved 2 tasks that SWE-2 Max high didn’t, and SWE-2 Max high solved 5 that GPT 6.1 Sol medium didn’t. Both solved 11; neither solved 6.

GPT 6.1 Sol medium only 2

  • stet-43493c52Passed tests
  • stet-commit-f8ae1177Passed tests

SWE-2 Max high only 5

  • stet-commit-f0caded9Passed tests
  • stet-2450ca2dPassed tests
  • stet-commit-60a0e6c2Passed tests
  • stet-commit-5e075641Passed tests
  • stet-commit-a8716b88Equivalent 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 6.1 Sol mediumSWE-2 Max highSolved 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-15439c21Passed testsEquivalent to the merged fixBoth
stet-66762b4cPassed testsPassed testsBoth
stet-commit-5d766ddeEquivalent to the merged fixPassed testsBoth
stet-commit-f0caded9FailedPassed testsSWE-2 Max high only
stet-43493c52Passed testsFailedGPT 6.1 Sol medium only
stet-6f84e978Equivalent to the merged fixPassed testsBoth
stet-2450ca2dFailedPassed testsSWE-2 Max high only
stet-commit-f8ae1177Passed testsFailedGPT 6.1 Sol medium only
stet-commit-342d0ac0Equivalent to the merged fixEquivalent to the merged fixBoth
stet-commit-60a0e6c2FailedPassed testsSWE-2 Max high only
stet-commit-5e075641FailedPassed testsSWE-2 Max high only
stet-commit-2826765eFailedFailedNeither
stet-commit-a8716b88FailedEquivalent to the merged fixSWE-2 Max high only
stet-commit-e928166fFailedFailedNeither
stet-commit-30506f8eFailedFailedNeither
stet-commit-87814583FailedFailedNeither
stet-commit-d2ab0c25FailedFailedNeither
stet-commit-e41c2e2dFailedFailedNeither

Side by side

Side by side
MetricGPT 6.1 Sol mediumSWE-2 Max high
Harnesscodexdevin
Reasoning effortmediumhigh
Rank3 of 152 of 15
Stet score64.195% range 54.3–73.465.195% range 55.2–74.7
Solved13/2410 passed, 3 judged equivalent16/2413 passed, 3 judged equivalent
Cost / task$1.10not recorded
Agent time / task11.8 min68.3 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 15 setups: bmk_d4ba310fdf50db4ccb2092e3.

See all 15 setups on the leaderboardHow Stet measures