Skip to the comparison
STET
Join the waitlist

Opus 4.8 medium vs Opus 5 medium

No clear quality winner: Opus 5 medium won 12, Opus 4.8 medium won 1, 11 tied; Opus 5 medium leads on cost and agent time: a little cheaper and a little faster.

24 tasksData from

Stet score

Opus 4.8 mediumclaude-code · medium reasoningRank 12 of 15

39.895% range 29.7–50.2

Opus 5 mediummedium reasoningRank 4 of 15

63.795% range 53.3–73.623.9 points higher

Their 95% score ranges don’t overlap.

Cost / task

Opus 4.8 medium$7.05
Opus 5 medium$6.78a little cheaper

Agent time / task

Opus 4.8 medium23.3 min
Opus 5 medium23.2 mina little faster

Quality

Head-to-head matchups

Opus 4.8 medium won1

Tied11

Opus 5 medium won12

Opus 5 medium’s win share 76%, 95% range 64–87%Ties are within judge noise.

Task by task

Opus 4.8 medium solved 1 task that Opus 5 medium didn’t, and Opus 5 medium solved 2 that Opus 4.8 medium didn’t. Both solved 12; neither solved 9.

Opus 4.8 medium only 1

  • stet-commit-60a0e6c2Passed tests

Opus 5 medium only 2

  • stet-2450ca2dPassed tests
  • stet-commit-2826765eEquivalent 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
TaskOpus 4.8 mediumOpus 5 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-15439c21Passed testsPassed testsBoth
stet-66762b4cPassed testsPassed testsBoth
stet-commit-5d766ddeEquivalent to the merged fixEquivalent to the merged fixBoth
stet-commit-f0caded9Equivalent to the merged fixPassed testsBoth
stet-43493c52Passed testsPassed testsBoth
stet-6f84e978Passed testsPassed testsBoth
stet-2450ca2dFailedPassed testsOpus 5 medium only
stet-commit-f8ae1177FailedFailedNeither
stet-commit-342d0ac0FailedFailedNeither
stet-commit-60a0e6c2Passed testsFailedOpus 4.8 medium only
stet-commit-5e075641FailedFailedNeither
stet-commit-2826765eFailedEquivalent to the merged fixOpus 5 medium only
stet-commit-a8716b88FailedFailedNeither
stet-commit-e928166fFailedFailedNeither
stet-commit-30506f8eFailedFailedNeither
stet-commit-87814583FailedFailedNeither
stet-commit-d2ab0c25FailedFailedNeither
stet-commit-e41c2e2dFailedFailedNeither

Side by side

Side by side
MetricOpus 4.8 mediumOpus 5 medium
Harnessclaude-code—
Reasoning effortmediummedium
Rank12 of 154 of 15
Stet score39.895% range 29.7–50.263.795% range 53.3–73.6
Solved13/2411 passed, 2 judged equivalent14/2412 passed, 2 judged equivalent
Cost / task$7.05$6.78
Agent time / task23.3 min23.2 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 15 setups: bmk_d4ba310fdf50db4ccb2092e3.

See all 15 setups on the leaderboardHow Stet measures