Partly: in 5 runs, Claude Opus 5.5's tailwindcss attribution reaches 4.1.0 (2025-04-01) and 4.2.0 (2026-02-18), inside tailwindcss 4, and stops there — tailwindcss was at 4.3.3 when this index last tested it (2026-09-28). That is ~4 to ~14 months below the training cutoff the subject stated in those runs (2026-06). 3 findings are currently charged against Claude Opus 5.5 on tailwindcss (2x S2 silently-wrong, 1x S3 deprecated), each reproduced in a published run and checked against tailwindcss's own release notes. Read the boundary precisely: it is the newest release whose contents the model can correctly attribute to that release, not the newest tailwindcss feature it can use. Past it a model often writes working code with a newer API while naming the wrong release for it.
Answer class inside, decided by one rule applied to every page
of this kind: every measured boundary is at or above the first release of the major named in the question. Every figure below is read from
the dataset at build time; nothing on this page is written by hand.
| Battery | Newest release it can place | Oldest it cannot | Lag vs stated cutoff |
|---|---|---|---|
| v4 2026-09-27 | 4.1.0 2025-04-01 |
4.2.0 2026-02-18 |
~14 months |
| v5-a 2026-09-27 | 4.1.0 2025-04-01 |
4.2.0 2026-02-18 |
~14 months |
| v5-b 2026-09-27 | 4.1.0 2025-04-01 |
4.2.0 2026-02-18 |
~14 months |
| v6-a 2026-09-28 | 4.2.0 2026-02-18 |
4.3.0 2026-05-08 |
~4 months |
| v6-b 2026-09-28 | 4.1.0 2025-04-01 |
4.2.0 2026-02-18 |
~14 months |
5 measurements of this pair, giving 2 different boundaries — 323 days apart, one release apart. Of those, 4 came in 2 groups: the draws inside a group were sent the same stored prompt file, concurrently and blind, and each group had its own file. 1 of the 2 agreed exactly and 1 disagreed, by 323 days, one release apart.
tailwindcss published 2 minor or major releases in the twelve months before this model’s stated cutoff, which is the scale a spread should be read against.
“Chargeable” means the change was published before this model’s own stated cutoff, so it had the opportunity to know it.
| Severity | Belief | Changed in | Chargeable | Proof |
|---|---|---|---|---|
| S2silently-wrong | Denies Tailwind ships scrollbar utilities, says the class names belong to a plugin, and rejects working markup that uses themscrollbar-auto / scrollbar-thin / scrollbar-none / scrollbar-thumb-* / scrollbar-track-* / scrollbar-gutter-* |
4.3.0 2026-05-08 |
yes | run · source |
| S2silently-wrong | Rejects zoom-50 and tab-4 as not core, in a review of markup where both compilezoom-* / tab-* |
4.3.0 2026-05-08 |
yes | run · source |
| S3deprecated | Denies @variant accepts a stacked or comma-separated variant, nests the AND and writes the OR block out three times@variant (stacked and compound variants) |
4.3.0 2026-05-08 |
yes | run · source |
The tailwindcss correction pack states what is true now for each corrected fact, with a primary-source citation, as markdown you can paste into a rules file (raw). What a correction pack measurably changed when one was tested — a pre-registered run on prisma and zod — is on the benchmark page, including where it changed nothing.
All of them at once: Which Claude model knows tailwindcss 4 best?
Other subjects on tailwindcss:
Claude Opus 5.5 on the other libraries: