Skip to the comparison

DeepSeek V4.1 Flash vs Opus 5

Opus 5 leads on quality and agent time: 17.3 points higher and 2.1× faster; DeepSeek V4.1 Flash leads on cost: 13.8× cheaper.

24 tasksData from

Stet score

DeepSeek V4.1 FlashRank 9 of 14

47.895% range 37.5–58.0

Opus 5Rank 3 of 14

65.195% range 54.8–74.917.3 points higher

A directional read: their 95% score ranges overlap.

Cost / task

DeepSeek V4.1 Flash$0.4913.8× cheaperfrom 23/24 tasks
Opus 5$6.78

Agent time / task

DeepSeek V4.1 Flash49.3 min
Opus 523.2 min2.1× faster

Task by task

DeepSeek V4.1 Flash solved 1 task that Opus 5 didn’t, and Opus 5 solved 3 that DeepSeek V4.1 Flash didn’t. Both solved 11; neither solved 9.

DeepSeek V4.1 Flash only 1

  • stet-commit-342d0ac0Equivalent to the merged fix

Opus 5 only 3

  • stet-6f84e978Passed tests
  • 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
TaskDeepSeek V4.1 FlashOpus 5Solved 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-f0caded9Passed testsPassed testsBoth
stet-commit-5d766ddePassed testsEquivalent to the merged fixBoth
stet-43493c52Passed testsPassed testsBoth
stet-6f84e978FailedPassed testsOpus 5 only
stet-commit-f8ae1177FailedFailedNeither
stet-2450ca2dFailedPassed testsOpus 5 only
stet-commit-342d0ac0Equivalent to the merged fixFailedDeepSeek V4.1 Flash only
stet-commit-60a0e6c2FailedFailedNeither
stet-commit-5e075641FailedFailedNeither
stet-commit-2826765eFailedEquivalent to the merged fixOpus 5 only
stet-commit-a8716b88FailedFailedNeither
stet-commit-30506f8eFailedFailedNeither
stet-commit-87814583FailedFailedNeither
stet-commit-d2ab0c25FailedFailedNeither
stet-commit-e41c2e2dFailedFailedNeither
stet-commit-e928166fFailedFailedNeither

Side by side

Side by side
MetricDeepSeek V4.1 FlashOpus 5
Rank9 of 143 of 14
Stet score47.895% range 37.5–58.065.195% range 54.8–74.9
Solved12/2411 passed, 1 judged equivalent14/2412 passed, 2 judged equivalent
Passed review8/249/231 not recorded
Matched merged change10/231 not recorded13/24
Cost / task$0.49from 23/24 tasks$6.78
How cost was recordedestimated from tokens on 23, not recorded on 1reported by its harness
Agent time / task49.3 min23.2 min
Ran inDaytona sandboxsandbox not recorded

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.

Changes up to 150 lines

11 tasks

11 tasks whose merged change was 2–149 lines in 1–2 files. The 7 small fixes below are among them.

Opus 5 matched the merged change more often: 10 of 11 to DeepSeek V4.1 Flash’s 7.

Changes up to 150 lines
DeepSeek V4.1 FlashOpus 5
Matched merged change7/1110/11
Passed review8/119/101 not recorded
Cost / task$0.21$1.50
Agent time / task34.9 min18.4 min

Small fixes

7 tasks

7 tasks whose instructions start with “Fix”. Their merged changes were 4–29 lines in 1–2 files.

Opus 5 matched the merged change more often: 7 of 7 to DeepSeek V4.1 Flash’s 5.

Small fixes
DeepSeek V4.1 FlashOpus 5
Matched merged change5/77/7
Passed review6/77/7
Cost / task$0.19$0.99
Agent time / task34.6 min15.9 min

Larger changes

13 tasks

13 tasks whose merged change ran over 150 lines or more than 3 files: 113–1,420 lines in 2–19 files.

Larger changes
DeepSeek V4.1 FlashOpus 5
Matched merged change3/121 not recorded3/13
Passed review0/130/13
Cost / task$0.751 not recorded$11.24
Agent time / task61.5 min27.2 min

From the leaderboard’s routing advice

  • Small fix: use Opus 5.

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