GPT 5.6 Luna max vs Haiku 5.5 max

GPT 5.6 Luna max leads on speed; Haiku 5.5 max on cost; quality is too close to call.

Quality: +1.1 pts; GPT 5.6 Luna max; 2–2 head to head, 19 tied
Speed: 2.0× faster; GPT 5.6 Luna max; 28.5 min vs 58.4 min per task
Cost: 1.2× cheaper; Haiku 5.5 max; $0.78 vs $0.90 per task

24 tasksData from November 6, 2026

Stet score

GPT 5.6 Luna maxmax reasoningRank 9 of 17

49.995% range 44.5–55.61.1 points higher

Haiku 5.5 maxmax reasoningRank 10 of 17

48.895% range 39.8–58.2

Other setups

SWE-2 Max high

58.4

Opus 5 medium

58.1

Pareto 26.9 medium

55.0

GPT 6.1 Sol medium

54.1

GPT 6 Sol medium

53.2

Grok 4.7 high

52.9

Muse Wonder Full low

52.1

DeepSeek V4.1 Flash max

50.6

GLM 5.3 Flash high

48.3

Opus 4.8 medium

47.0

GPT 6 Luna max

46.5

Haiku 5.5 low

45.1

GPT 5.6 Luna low

45.0

GPT 6 Luna low

40.3

Muse Spark 1.3 high

47.8

A directional read: their 95% score ranges overlap.

Quality

Head-to-head matchups

GPT 5.6 Luna max won2

Tied19

Haiku 5.5 max won2

1 undecided

GPT 5.6 Luna max’s win share 50%, 95% range 41–59%Ties are within judge noise.

Task by task

GPT 5.6 Luna max solved 4 tasks that Haiku 5.5 max didn’t, and Haiku 5.5 max solved 4 that GPT 5.6 Luna max didn’t. Both solved 6; neither solved 9.

stet-232b50baSolved by 16 of 17 setups

GPT 5.6 Luna maxPassed tests
Haiku 5.5 maxFailed

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. 1 of the 24 tasks is left out because one of the two has no scored result on it.

All 23 compared tasks

Task by task
Task	GPT 5.6 Luna max	Haiku 5.5 max	Solved by
`stet-232b50ba`	Passed tests	Failed	GPT 5.6 Luna max only
`stet-3169aefa`	Passed tests	Passed tests	Both
`stet-5276aa3f`	Passed tests	Passed tests	Both
`stet-89dfbc27`	Passed tests	Passed tests	Both
`stet-b28f4fe7`	Passed tests	Passed tests	Both
`stet-commit-bbbbae09`	Passed tests	Passed tests	Both
`stet-66762b4c`	Equivalent to the merged fix	Failed	GPT 5.6 Luna max only
`stet-commit-5d766dde`	Equivalent to the merged fix	Equivalent to the merged fix	Both
`stet-commit-f0caded9`	Equivalent to the merged fix	Failed	GPT 5.6 Luna max only
`stet-43493c52`	Passed tests	Failed	GPT 5.6 Luna max only
`stet-commit-f8ae1177`	Failed	Failed	Neither
`stet-15439c21`	Failed	Passed tests	Haiku 5.5 max only
`stet-2450ca2d`	Failed	Passed tests	Haiku 5.5 max only
`stet-commit-342d0ac0`	Failed	Equivalent to the merged fix	Haiku 5.5 max only
`stet-6f84e978`	Failed	Equivalent to the merged fix	Haiku 5.5 max only
`stet-commit-5e075641`	Failed	Failed	Neither
`stet-commit-2826765e`	Failed	Failed	Neither
`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	GPT 5.6 Luna max	Haiku 5.5 max
Reasoning effort	max	max
Rank	9 of 17	10 of 17
Stet score	49.995% range 44.5–55.6	48.895% range 39.8–58.2
Solved	10/247 passed, 3 judged equivalent	10/247 passed, 3 judged equivalent
Cost / task	$0.90	$0.78
Agent time / task	28.5 min	58.4 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 November 6, 2026.
Both setups come from the same leaderboard run of 17 setups: bmk_d4ba310fdf50db4ccb2092e3.

See all 17 setups on the leaderboard How Stet measures