Grok 4.7 high vs Opus 5 medium

No clear quality winner: Opus 5 medium won 7, Grok 4.7 high won 6, 11 tied; Grok 4.7 high leads on cost and agent time: 1.2× cheaper and 1.2× faster.

24 tasksData from October 29, 2026

Stet score

Grok 4.7 highcursor · high reasoningRank 5 of 15

62.195% range 51.7–71.7

Opus 5 mediummedium reasoningRank 4 of 15

63.795% range 53.3–73.61.6 points higher

Other setups

Muse Wonder Full low

72.4

SWE-2 Max high

65.1

GPT 6.1 Sol medium

64.1

Pareto 26.9 medium

58.4

Haiku 5.5 max

57.1

GPT 6 Sol medium

57.0

GPT 6 Luna max

49.2

DeepSeek V4.1 Flash max

46.9

Haiku 5.5 low

40.1

Opus 4.8 medium

39.8

Muse Spark 1.3 high

32.8

GLM 5.3 Flash high

29.9

GPT 6 Luna low

20.4

A directional read: their 95% score ranges overlap.

Cost / task

Grok 4.7 high$5.761.2× cheaper

Opus 5 medium$6.78

Agent time / task

Grok 4.7 high18.9 min1.2× faster

Opus 5 medium23.2 min

Quality

Head-to-head matchups

Grok 4.7 high won6

Tied11

Opus 5 medium won7

Grok 4.7 high’s win share 52%, 95% range 36–67%Ties are within judge noise.

Task by task

Grok 4.7 high solved 1 task that Opus 5 medium didn’t, and Opus 5 medium solved 2 that Grok 4.7 high didn’t. Both solved 12; neither solved 9.

Grok 4.7 high only 1

stet-commit-f8ae1177Passed tests

Opus 5 medium only 2

stet-43493c52Passed 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
Task	Grok 4.7 high	Opus 5 medium	Solved by
`stet-3169aefa`	Passed tests	Passed tests	Both
`stet-89dfbc27`	Passed tests	Passed tests	Both
`stet-b28f4fe7`	Passed tests	Passed tests	Both
`stet-232b50ba`	Passed tests	Passed tests	Both
`stet-5276aa3f`	Passed tests	Passed tests	Both
`stet-commit-bbbbae09`	Passed tests	Passed tests	Both
`stet-15439c21`	Passed tests	Passed tests	Both
`stet-66762b4c`	Passed tests	Passed tests	Both
`stet-commit-5d766dde`	Equivalent to the merged fix	Equivalent to the merged fix	Both
`stet-commit-f0caded9`	Equivalent to the merged fix	Passed tests	Both
`stet-43493c52`	Failed	Passed tests	Opus 5 medium only
`stet-6f84e978`	Passed tests	Passed tests	Both
`stet-2450ca2d`	Passed tests	Passed tests	Both
`stet-commit-f8ae1177`	Passed tests	Failed	Grok 4.7 high only
`stet-commit-342d0ac0`	Failed	Failed	Neither
`stet-commit-60a0e6c2`	Failed	Failed	Neither
`stet-commit-5e075641`	Failed	Failed	Neither
`stet-commit-2826765e`	Failed	Equivalent to the merged fix	Opus 5 medium only
`stet-commit-a8716b88`	Failed	Failed	Neither
`stet-commit-e928166f`	Failed	Failed	Neither
`stet-commit-30506f8e`	Failed	Failed	Neither
`stet-commit-87814583`	Failed	Failed	Neither
`stet-commit-d2ab0c25`	Failed	Failed	Neither
`stet-commit-e41c2e2d`	Failed	Failed	Neither

Side by side

Side by side
Metric	Grok 4.7 high	Opus 5 medium
Harness	cursor	—
Reasoning effort	high	medium
Rank	5 of 15	4 of 15
Stet score	62.195% range 51.7–71.7	63.795% range 53.3–73.6
Solved	13/2411 passed, 2 judged equivalent	14/2412 passed, 2 judged equivalent
Cost / task	$5.76	$6.78
Agent time / task	18.9 min	23.2 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 October 29, 2026.
Both setups come from the same leaderboard run of 15 setups: bmk_d4ba310fdf50db4ccb2092e3.

See all 15 setups on the leaderboard How Stet measures