Skip to the comparison
STET
Join the waitlist

DeepSeek V4.1 Flash max vs GPT 6.1 Sol medium

No clear quality winner: GPT 6.1 Sol medium won 12, DeepSeek V4.1 Flash max won 3, 9 tied; DeepSeek V4.1 Flash max leads on cost: 2.2× cheaper; GPT 6.1 Sol medium leads on agent time: 4.2× faster.

24 tasksData from

Stet score

DeepSeek V4.1 Flash maxdeepseek-harness · max reasoningRank 11 of 16

45.995% range 35.5–56.1

GPT 6.1 Sol mediumcodex · medium reasoningRank 4 of 16

62.595% range 53.0–71.716.6 points higher

A directional read: their 95% score ranges overlap.

Cost / task

DeepSeek V4.1 Flash max$0.492.2× cheaperfrom 23/24 tasks
GPT 6.1 Sol medium$1.10

Agent time / task

DeepSeek V4.1 Flash max49.3 min
GPT 6.1 Sol medium11.8 min4.2× faster

Quality

Head-to-head matchups

DeepSeek V4.1 Flash max won3

Tied9

GPT 6.1 Sol medium won12

GPT 6.1 Sol medium’s win share 69%, 95% range 54–82%Ties are within judge noise.

Task by task

DeepSeek V4.1 Flash max solved 1 task that GPT 6.1 Sol medium didn’t, and GPT 6.1 Sol medium solved 2 that DeepSeek V4.1 Flash max didn’t. Both solved 11; neither solved 10.

DeepSeek V4.1 Flash max only 1

  • stet-commit-f0caded9Passed tests

GPT 6.1 Sol medium only 2

  • stet-6f84e978Equivalent to the merged fix
  • stet-commit-f8ae1177Passed 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
TaskDeepSeek V4.1 Flash maxGPT 6.1 Sol 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-66762b4cPassed testsPassed testsBoth
stet-15439c21Passed testsPassed testsBoth
stet-commit-5d766ddePassed testsEquivalent to the merged fixBoth
stet-43493c52Passed testsPassed testsBoth
stet-commit-f0caded9Passed testsFailedDeepSeek V4.1 Flash max only
stet-6f84e978FailedEquivalent to the merged fixGPT 6.1 Sol medium only
stet-2450ca2dFailedFailedNeither
stet-commit-342d0ac0Equivalent to the merged fixEquivalent to the merged fixBoth
stet-commit-f8ae1177FailedPassed testsGPT 6.1 Sol medium only
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
MetricDeepSeek V4.1 Flash maxGPT 6.1 Sol medium
Harnessdeepseek-harnesscodex
Reasoning effortmaxmedium
Rank11 of 164 of 16
Stet score45.995% range 35.5–56.162.595% range 53.0–71.7
Solved12/2411 passed, 1 judged equivalent13/2410 passed, 3 judged equivalent
Cost / task$0.49from 23/24 tasks$1.10
Agent time / task49.3 min11.8 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