Does Claude Opus 5 know better-auth 1?

Partly: in 13 runs, Claude Opus 5's better-auth attribution reaches 1.2.0 (2025-03-01) and 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 ~10 to ~26 months below the training cutoff the subject stated in those runs (2026-05). 5 findings are currently charged against Claude Opus 5 on better-auth (1x S1 breaks-build, 3x S2 silently-wrong, 1x S3 deprecated), 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
~10 months
v1r-a 2026-09-01 1.3.0
2025-07-19
1.4.0
2025-11-22
~10 months
v1r-b 2026-09-01 1.3.0
2025-07-19
1.4.0
2025-11-22
~10 months
v2-a 2026-09-02 1.3.0
2025-07-19
1.4.0
2025-11-22
~10 months
v2-b 2026-09-02 1.3.0
2025-07-19
1.4.0
2025-11-22
~10 months
v3-a 2026-09-03 1.2.0
2025-03-01
1.3.0
2025-07-19
~22 months
v3-b 2026-09-03 1.2.0
2025-03-01
1.3.0
2025-07-19
~22 months
v4-c 2026-09-03 1.2.0
2025-03-01
1.3.0
2025-07-19
~22 months
v4-d 2026-09-03 1.2.0
2025-03-01
1.3.0
2025-07-19
~22 months
v5-a 2026-09-03 1.2.0
2025-03-01
1.3.0
2025-07-19
~22 months
v5-b 2026-09-03 1.2.0
2025-03-01
1.3.0
2025-07-19
~22 months
v7-a 2026-09-06 1.2.0
2025-03-01
1.3.0
2025-07-19
~26 months
v7-b 2026-09-06 1.2.0
2025-03-01
1.3.0
2025-07-19
~26 months

How repeatable is this?

13 measurements of this pair, giving 2 different boundaries — 140 days apart, one release apart. Of those, 2 came from the same stored prompt file, sent concurrently and blind: they agreed exactly.

better-auth published 4 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 Opus 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
S1breaks-build Invents an at-rest storage option on the phone-number plugin, and ships phoneNumber({ storeOTP: 'hashed' }) as the fix for the threat-model row
phoneNumber({ storeOTP })
1.3.0
2025-07-19
yes run · source
S2silently-wrong Denies that better-auth can run with no session store at all, and sends the reader to Redis or the jwt plugin instead
stateless / database-less sessions
1.4.0
2025-11-22
yes run · source
S2silently-wrong Denies that baseURL can be anything but a static string, and routes a multi-domain deployment through a canonical auth host instead
baseURL as a dynamic multi-host config
1.5.0
2026-03-01
yes run · source
S2silently-wrong Denies the email-OTP plugin has a resend-reuse option and ships a Redis cache in front of generateOTP instead of resendStrategy: 'reuse'
emailOTP({ resendStrategy })
1.5.6
2026-03-22
yes run · source
S3deprecated Denies the two-factor client plugin takes a page option — while naming twoFactorPage correctly and asserting it was removed rather than added
twoFactorClient({ twoFactorPage })
1.5.6
2026-03-22
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 Opus 5 on the other libraries: