Task gallery / Games / Version 1
Task evidence / console

arb-desk

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

The task

You are hired onto an arbitrage desk. The prize is a trading season, and the market is one asset listed on four separate venues. Each venue keeps its own integer order book -- a ladder of price levels, four lots to a level -- and quotes around a hidden fair value plus a per-venue basis that drifts. When the basis pulls the venues apart, one venue's best ask sits below another's best bid: a spatial arbitrage, free mo…

Excerpt only; not a complete executable task specification. Task ID task_9403da6e6d1f48a2 · 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_2716e84170064f6c
oracle@@		Oct 10, 2026
console		1 · validNo diagnostic label
derived		Tokens: —
Turns: —
Cost: —		Not publicly available
trial_527cb935b466400a
nop@@		Oct 10, 2026
console		0 · validNo diagnostic label
derived		Tokens: —
Turns: —
Cost: —		Not publicly available
trial_040fb6cb225143c8
Claude Opus 5 · default (unverified)		Oct 10, 2026
console		1 · validGOOD_SUCCESS
frozen-classifier		Tokens: 150,129
Turns: 52
Cost: $9.7983		Not publicly available
trial_0d358b636a964769
Claude Opus 5 · default (unverified)		Oct 10, 2026
console		1 · validGOOD_SUCCESS
frozen-classifier		Tokens: 152,326
Turns: 85
Cost: $13.5109		Not publicly available
trial_35d1c67dc3024927
Claude Opus 5 · default (unverified)		Oct 10, 2026
console		1 · validGOOD_SUCCESS
frozen-classifier		Tokens: 181,111
Turns: 102
Cost: $17.0357		Not publicly available
trial_71f501d601db4427
Claude Opus 5 · default (unverified)		Oct 10, 2026
console		1 · validGOOD_SUCCESS
frozen-classifier		Tokens: 197,725
Turns: 95
Cost: $16.7054		Not publicly available
trial_c568e7b5dd2c4bf8
Claude Opus 5 · default (unverified)		Oct 10, 2026
console		1 · validGOOD_SUCCESS
frozen-classifier		Tokens: 177,972
Turns: 130
Cost: $19.4505		Not publicly available