Task gallery / Games / Version 1
Task evidence / console

alchemy-cauldron

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

The task

You're entered as the programmer in a bot tournament for the Alembic Bench, a small two-alchemist synthesis duel. You drive the ALCHEMIST: a still of eleven flasks in a row, each holding one reagent (a letter). A commission crystallises the instant FOUR flasks IN A ROW all hold the pure elixir. Across the bench a RIVAL alchemist works the same rack against you, one transmutation at a time, trying to make sure that n…

Excerpt only; not a complete executable task specification. Task ID task_11dc705631944c69 · 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 / effortVerifier result [95% Wilson]Diagnostic labels / validHARNESS_ERROR · excludedOutcome classes
Claude Opus 5 · default (unverified)5/5 · 100.0% [56.6%, 100.0%]5 / 50
GOOD_FAILURE: 0
BAD_FAILURE: 0
GOOD_SUCCESS: 5
BAD_SUCCESS: 0

Legacy evidence

Model / effortVerifier result [95% Wilson]Diagnostic labels / validHARNESS_ERROR · excludedOutcome classes

Difficulty, with uncertainty

Selected-best difficulty: 0.0% [0.0%, 43.4%]. This is one minus the best measured current-row pass rate among rows with at least five valid runs.

The maximum is selected from the observed rows, so the estimate is optimistic. Its Wilson interval is not adjusted for model selection. “Hard” requires qualifying GOOD_FAILURE evidence; the threshold flag additionally requires the interval and recorded quality gates to meet the documented rule. This is not independent validation. Threshold flag: no.

Every recorded run

7 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 / modelDate / sourceReward / eligibilityDiagnostic class / sourceResourcesEvidence
trial_d1a887f42b794f2d
oracle@@		Oct 10, 2026
console		1 · validNo diagnostic label
derived		Tokens: —
Turns: —
Cost: —		Not publicly available
trial_eb38f71d2bb74fd3
nop@@		Oct 10, 2026
console		0 · validNo diagnostic label
derived		Tokens: —
Turns: —
Cost: —		Not publicly available
trial_5ff0dccb4b334ad6
Claude Opus 5 · default (unverified)		Oct 10, 2026
console		1 · validGOOD_SUCCESS
frozen-classifier		Tokens: 164,304
Turns: 110
Cost: $15.8038		Not publicly available
trial_8b98ad923f894755
Claude Opus 5 · default (unverified)		Oct 10, 2026
console		1 · validGOOD_SUCCESS
frozen-classifier		Tokens: 171,631
Turns: 117
Cost: $16.7274		Not publicly available
trial_ddac3e038a7141c6
Claude Opus 5 · default (unverified)		Oct 10, 2026
console		1 · validGOOD_SUCCESS
frozen-classifier		Tokens: 207,559
Turns: 168
Cost: $25.7755		Not publicly available
trial_e09abeadebf0479b
Claude Opus 5 · default (unverified)		Oct 10, 2026
console		1 · validGOOD_SUCCESS
frozen-classifier		Tokens: 141,440
Turns: 151
Cost: $16.5073		Not publicly available
trial_f8ad279487b245b1
Claude Opus 5 · default (unverified)		Oct 10, 2026
console		1 · validGOOD_SUCCESS
frozen-classifier		Tokens: 194,639
Turns: 169
Cost: $25.5184		Not publicly available