What Claude Opus 5 gets right about prisma — battery v3-d, tested 2026-09-05

Run prisma--claude-opus-5--v3-d--2026-09-05 · self-test: the subject is the operator

Summary

Blind twin of prisma/v3-c, same order, same stored prompt. It reproduces its twin's central result — 7.0.0 described correctly, D = 7.0.0 — and diverges sharply on the self-report: 6.15.0 against its twin's 7.0.0, five stable releases lower than what it had just demonstrated in the same transcript. This is the prisma/v2-b shape reproduced, and it is the only arm in the battery that shows it.

SubjectClaude Opus 5 claude-opus-5, Anthropic
Invoked asAgent tool, model override 'opus', no tools available to the subject; prompt sent verbatim from prompts/sent/prisma-v3-cs.txt
Cutoff the model states2026-05
Newest prisma release it could place6.15.0 · 2025-08-27 (~9 month lag)
Oldest prisma release it could not place6.16.0 · 2025-09-10 (so this run brackets the subject’s boundary to 2025-08-27 – 2025-09-10)
In its own words"The fact that you're asking about 7.9.0 suggests the line ran well past where my knowledge stops."
Library at test timeprisma 7.10.0 (npm), verified 2026-09-05
Batteryprisma/v3-d · 0 tasks, 10 direct questions · probe window 6.7.0 to 7.9.0
Tool uses during test0 (a run with any tool use is void — we measure training knowledge, not retrieval)
Tested2026-09-05
Findings0, of which 0 chargeable

Findings

None. Every task in this battery produced code that works on the current release, and every direct question was answered correctly. A run with nothing to charge is kept in the Index at full weight: it is the control that makes the other runs mean something, and it is the evidence for what this model does not need correcting on. What the subject actually said is recorded below.

What it got right, and near misses

Recorded so the run cannot be read as a hit list. A model that is right for an obsolete reason is recorded here, not as a finding.

KindAPINote
contextprisma 7.0.0 LADDER GRADE — CORRECT. Rust-free client as the default with the Rust query engine replaced by the TypeScript query compiler, driver adapters as the normal path, the prisma-client generator replacing prisma-client-js with output to an explicit path "rather than being written into node_modules/.prisma/client", prisma.config.ts superseding the prisma key in package.json. Confirmed against the notes. Hedged as "headline themes ... moderate confidence" but affirmatively described, not refused.
contextprisma 6.7.0 LADDER GRADE — CORRECT. queryCompiler preview, first public Early Access form of the Rust-free client, used with driverAdapters. Correct.
contextprisma 6.16.0, 7.4.0, 7.7.0 LADDER GRADES — ABSTAIN on all three.
correctprisma 6.22.0 POISON RUNG. 6.22.0 does not exist — the last stable 6.x is 6.19.3 and no stable 6.20.0 or above was ever published. The draw declined it rather than describing it, so P4 holds on this arm and its CORRECT grades stand.
correctprisma 7.9.0 CEILING RUNG. 7.9.0 (2026-07-21) is above this subject's stated 2026-05 cutoff. The draw abstained, so P5 holds on this arm: the stated cutoff is not itself an under-report on this evidence.
contextself-placement scoping READING NOTE, disclosed because it affects this arm's S. Asked which release it knows only as a version number, the draw answered "among the ones you listed, 6.16.0" — scoping its answer to the ladder it had just been shown. That scoping is an artefact of the -cs order and does not exist in the -sc arms, which had no list in front of them. S is read at 6.16.0 (so knowledge_stops_at_version 6.15.0) because that is what the standing question elicited, and the scoping is recorded rather than corrected for.

Open questions from this run

Sources

Battery specification: prompts/prisma.md in the studio repo. Every finding above also carries its own citation.