bignum-arithmetic · Syncvals

Task gallery / Software engineering / Version 1

Reference solution (oracle): Pass
No-op resistance check: Pass
QA verdict: Not recorded
Aggregate eligibility: Eligible version

The task

Reproduce the GNU GMP integer layer (mpz) from C in Rust Reimplement the integer (mpz) layer of the GNU Multiple Precision arithmetic library ([gmplib.org]([source link]), release gmp-6.3.0) from scratch in Rust under /app, producing a binary whose output is byte-for-byte identical to a reference driver linked against the real libgmp on a held-out battery. Frozen CLI (the grader calls this directly — do not cha…

Excerpt only; not a complete executable task specification. Task ID task_d6a60c4029734f27 · version 1. Selection status: not fully recorded.

Results by model and effort

This exact task version only. Every rate is passes / valid runs with a Wilson 95% interval; n≤2 remains counts only. Macro aggregation does not apply within a single task. Baselines are summarized in the quality gates, not ranked. A passed no-op resistance check means that doing nothing did not solve the task.

Current evidence

Model / effort	Verifier result [95% Wilson]	Diagnostic labels / valid	HARNESS_ERROR · excluded	Outcome classes
Claude Opus 5 · default (unverified)	0/4 · 0.0% [0.0%, 49.0%] · preliminary	4 / 4	1	GOOD_FAILURE: 3 BAD_FAILURE: 1 GOOD_SUCCESS: 0 BAD_SUCCESS: 0

Legacy evidence

Model / effort	Verifier result [95% Wilson]	Diagnostic labels / valid	HARNESS_ERROR · excluded	Outcome classes

Every recorded run

10 recorded trials, including controls. Diagnostic labels do not replace verifier reward. Labels and quality checks are source declarations, not independently attested here. Internal evidence remains private; a missing public URL is shown explicitly. Records with invalid or absent rewards are not scored.

Run / model	Date / source	Reward / eligibility	Diagnostic class / source	Resources	Evidence
`trial_ad35fc42d2114279` oracle@@	Oct 10, 2026 console	No reward · excludedno_reward	No diagnostic label No diagnostic source	Tokens: — Turns: — Cost: —	Not publicly available
`trial_adc3b12541df4dbf` nop@@	Oct 10, 2026 console	No reward · excludedno_reward	No diagnostic label No diagnostic source	Tokens: — Turns: — Cost: —	Not publicly available
`trial_1471a56466514f42` oracle@@	Oct 11, 2026 console	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_f62c9c68c6984bed` nop@@	Oct 11, 2026 console	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_2a14d0bc39b243c7` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: 299,277 Turns: 146 Cost: $30.1586	Not publicly available
`trial_3b47c5e890f945e4` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: 218,746 Turns: 137 Cost: $21.4007	Not publicly available
`trial_4981ef8021a746bd` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	0 · excludedharness_error	HARNESS_ERROR frozen-classifier	Tokens: 62,499 Turns: 18 Cost: $3.1446	Not publicly available
`trial_812c614bd8774c5a` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	0 · valid	BAD_FAILURE frozen-classifier	Tokens: 245,452 Turns: 111 Cost: $20.3156	Not publicly available
`trial_918cbd5f38c042ab` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: 235,008 Turns: 162 Cost: $25.5209	Not publicly available
`trial_e4f51b6425ad4d88` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	No reward · excludedno_reward	No diagnostic label No diagnostic source	Tokens: — Turns: — Cost: —	Not publicly available