Grok 4.7 high vs SWE-2 Max high

Grok 4.7 high leads on speed; quality is too close to call.

Quality: +3.6 pts; SWE-2 Max high; 11–6 head to head, 7 tied
Speed: 3.6× faster; Grok 4.7 high; 18.9 min vs 68.3 min per task

24 tasksData from October 29, 2026Cost not recorded for SWE-2 Max high

Stet score

Grok 4.7 highcursor · high reasoningRank 4 of 14

60.795% range 50.1–70.2

SWE-2 Max highdevin · high reasoningRank 1 of 14

64.395% range 54.3–73.93.6 points higher

Other setups

GPT 6.1 Sol medium

62.5

Opus 5 medium

62.3

Pareto 26.9 medium

57.1

Haiku 5.5 max

55.5

GPT 6 Sol medium

55.4

GPT 6 Luna max

47.4

DeepSeek V4.1 Flash max

45.9

Opus 4.8 medium

39.2

Haiku 5.5 low

38.9

Muse Spark 1.3 high

31.9

GLM 5.3 Flash high

29.0

GPT 6 Luna low

19.9

A directional read: their 95% score ranges overlap.

Quality

Head-to-head matchups

Grok 4.7 high won6

Tied7

SWE-2 Max high won11

SWE-2 Max high’s win share 59%, 95% range 43–75%Ties are within judge noise.

Task by task

Grok 4.7 high solved 1 task that SWE-2 Max high didn’t, and SWE-2 Max high solved 4 that Grok 4.7 high didn’t. Both solved 12; neither solved 7.

On the 12 tasks both solved, judges preferred SWE-2 Max high’s patch on 4, Grok 4.7 high’s on 3, and called 5 even.

stet-commit-f8ae1177Solved by 6 of 14 setups

Grok 4.7 highPassed tests
SWE-2 Max highFailed

Judges preferred Grok 4.7 high’s patch

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
Task	Grok 4.7 high	SWE-2 Max high	Solved by	Better patch
`stet-3169aefa`	Passed tests	Passed tests	Both	Grok 4.7 high
`stet-89dfbc27`	Passed tests	Passed tests	Both	Grok 4.7 high
`stet-b28f4fe7`	Passed tests	Passed tests	Both	Even
`stet-232b50ba`	Passed tests	Passed tests	Both	Even
`stet-5276aa3f`	Passed tests	Passed tests	Both	Even
`stet-commit-bbbbae09`	Passed tests	Passed tests	Both	Even
`stet-15439c21`	Passed tests	Equivalent to the merged fix	Both	SWE-2 Max high
`stet-66762b4c`	Passed tests	Passed tests	Both	Grok 4.7 high
`stet-commit-f0caded9`	Equivalent to the merged fix	Passed tests	Both	SWE-2 Max high
`stet-commit-5d766dde`	Equivalent to the merged fix	Passed tests	Both	SWE-2 Max high
`stet-43493c52`	Failed	Failed	Neither	SWE-2 Max high
`stet-6f84e978`	Passed tests	Passed tests	Both	SWE-2 Max high
`stet-commit-f8ae1177`	Passed tests	Failed	Grok 4.7 high only	Grok 4.7 high
`stet-2450ca2d`	Passed tests	Passed tests	Both	Even
`stet-commit-342d0ac0`	Failed	Equivalent to the merged fix	SWE-2 Max high only	SWE-2 Max high
`stet-commit-60a0e6c2`	Failed	Passed tests	SWE-2 Max high only	SWE-2 Max high
`stet-commit-5e075641`	Failed	Passed tests	SWE-2 Max high only	SWE-2 Max high
`stet-commit-2826765e`	Failed	Failed	Neither	SWE-2 Max high
`stet-commit-a8716b88`	Failed	Equivalent to the merged fix	SWE-2 Max high only	SWE-2 Max high
`stet-commit-30506f8e`	Failed	Failed	Neither	Even
`stet-commit-87814583`	Failed	Failed	Neither	Grok 4.7 high
`stet-commit-d2ab0c25`	Failed	Failed	Neither	Grok 4.7 high
`stet-commit-e41c2e2d`	Failed	Failed	Neither	SWE-2 Max high
`stet-commit-e928166f`	Failed	Failed	Neither	Even

Side by side

Side by side
Metric	Grok 4.7 high	SWE-2 Max high
Harness	cursor	devin
Reasoning effort	high	high
Rank	4 of 14	1 of 14
Stet score	60.795% range 50.1–70.2	64.395% range 54.3–73.9
Solved	13/2411 passed, 2 judged equivalent	16/2413 passed, 3 judged equivalent
Cost / task	$5.76	not recorded
Agent time / task	18.9 min	68.3 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 October 29, 2026.
Both setups come from the same leaderboard run of 14 setups: bmk_d4ba310fdf50db4ccb2092e3.

See all 14 setups on the leaderboard How Stet measures