Not by version attribution: in 4 runs, Claude Sonnet 5 places its prisma boundary at 6.0.0 (2024-11-28) — below prisma 7.0.0 (2025-11-19), the first release of prisma 7. That is ~14 months below the training cutoff the subject stated in those runs (2026-01). 14 findings are currently charged against Claude Sonnet 5 on prisma (7x S1 breaks-build, 4x S2 silently-wrong, 1x S3 deprecated, 2x S4 wrong-metadata), each reproduced in a published run and checked against prisma'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 prisma 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 below, decided by one rule applied to every page
of this kind: every measured boundary is below 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 |
|---|---|---|---|
| v1 2026-08-31 | 6.0.0 2024-11-28 |
6.1.0 2024-12-17 |
~14 months |
| v2-c 2026-09-05 | 6.0.0 2024-11-28 |
6.1.0 2024-12-17 |
~14 months |
| v5-a 2026-09-06 | 6.0.0 2024-11-28 |
6.1.0 2024-12-17 |
~14 months |
| v5-b 2026-09-06 | 6.0.0 2024-11-28 |
6.1.0 2024-12-17 |
~14 months |
1 further run of this pair established only one end of the interval, or measured the instrument rather than the library; it is listed under Runs below.
4 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.
prisma published 21 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 |
|---|---|---|---|---|
| S1breaks-build | Constructs the client with no arguments, in four separate answersnew PrismaClient() |
7.0.0 2025-11-19 |
yes | run · source |
| S1breaks-build | Generator block with no output pathgenerator client { output } |
7.0.0 2025-11-19 |
yes | run · source |
| S1breaks-build | Imports PrismaClient from @prisma/clientimport { PrismaClient } from '@prisma/client' |
7.0.0 2025-11-19 |
yes | run · source |
| S1breaks-build | No config file at all; the datasource URL stays in schema.prismaprisma.config.ts |
7.0.0 2025-11-19 |
yes | run · source |
| S1breaks-build | Seed command declared in package.json, with the implicit-run claim attachedpackage.json prisma key |
7.0.0 2025-11-19 |
yes | run · source |
| S1breaks-build | Recommends prisma generate --no-engineprisma generate --no-engine |
7.0.0 2025-11-19 |
yes | run · source |
| S1breaks-build | migrate diff with the removed --from-url / --to-schema-datamodel flagsprisma migrate diff |
7.0.0 2025-11-19 |
yes | run · source |
| S2silently-wrong | Assumes the CLI loads .env by itselfautomatic .env loading |
7.0.0 2025-11-19 |
yes | run · source |
| S2silently-wrong | Relies on the postinstall hook to generate the client in Dockerpostinstall prisma generate |
7.0.0 2025-11-19 |
yes | run · source |
| S2silently-wrong | Whole deployment story built around a query-engine binary that no longer shipsengineType |
7.0.0 2025-11-19 |
yes | run · source |
| S2silently-wrong | Denies that Prisma ships a first-party SQLCommenter plugin@prisma/sqlcommenter-query-insights |
7.1.0 2025-12-04 |
yes | run · source |
| S3deprecated | Uses the superseded generator provider throughoutprovider = "prisma-client-js" |
7.0.0 2025-11-19 |
yes | run · source |
| S4wrong-metadata | Knowledge stops at 6.0.0 — fourteen months before its own stated cutoff | 6.1.0 2024-12-17 |
yes | run · source |
| S4wrong-metadata | Sets a MongoDB team up on a version that dropped MongoDB, with no version caveatMongoDB support |
7.0.0 2025-11-19 |
yes | run · source |
The prisma 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.
All of them at once: Which Claude model knows prisma 7 best?
Other subjects on prisma:
Claude Sonnet 5 on the other libraries: