Does Claude Fable 5 know better-auth 1?

Partly: in 7 runs, Claude Fable 5's better-auth attribution reaches 1.3.0 (2025-07-19), inside better-auth 1, and stops there — better-auth was at 1.7.3 when this index last verified against it (2026-09-06). That is ~6 to ~18 months below the training cutoff the subject stated in those runs (2026-01). 2 findings are currently charged against Claude Fable 5 on better-auth (2x S2 silently-wrong), each reproduced in a published run and checked against better-auth'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 better-auth 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.

The measurements

BatteryNewest release it can placeOldest it cannotLag vs stated cutoff
v1 2026-09-01 1.3.0
2025-07-19
1.4.0
2025-11-22
~6 months
v2-a 2026-09-02 1.3.0
2025-07-19
1.4.0
2025-11-22
~6 months
v2-b 2026-09-02 1.3.0
2025-07-19
1.4.0
2025-11-22
~6 months
v3-d 2026-09-03 1.3.0
2025-07-19
1.4.0
2025-11-22
~18 months
v4-e 2026-09-03 1.3.0
2025-07-19
1.4.0
2025-11-22
~18 months
v4-f 2026-09-03 1.3.0
2025-07-19
1.4.0
2025-11-22
~18 months
v5-d 2026-09-03 1.3.0
2025-07-19
1.4.0
~6 months

How repeatable is this?

6 measurements of this pair, all giving the same boundary. Of those, 2 came from the same stored prompt file, sent concurrently and blind: they agreed exactly.

better-auth published 3 minor or major releases in the twelve months before this model’s stated cutoff, which is the scale a spread should be read against.

What Claude Fable 5 gets wrong about better-auth

“Chargeable” means the change was published before this model’s own stated cutoff, so it had the opportunity to know it.

SeverityBeliefChanged inChargeableProof
S2silently-wrong States that better-auth offers no stateless, store-free session mode, and names cookieCache, Redis and the jwt plugin as the only options
stateless / database-less sessions
1.4.0
2025-11-22
yes run · source
S2silently-wrong States that operating with no server-side session state is not what the library supports, which stopped being true in 1.4.0
stateless session management
1.4.0
2025-11-22
yes run · source

What to do about it

The better-auth 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 zod — is on the benchmark page, including where it changed nothing.

Runs

The same question, asked of the others

All of them at once: Which Claude model knows better-auth 1 best?

Other subjects on better-auth:

Claude Fable 5 on the other libraries: