Task gallery / SWE-Marathon / Version 1
Task evidence / console

implement-yaml2json

high-fail (unreviewed)Current calibratedChosen benchmark version
Reference solution (oracle)
Unverified
No-op resistance check
Unverified
QA verdict
Not recorded
Aggregate eligibility
Eligible version

The task

Reimplement yaml2json from scratch You are given a working binary at /app/oraclebinary/yaml2json that implements [yaml2json]([source link]) at commit v1.3.5. Your task is to reimplement that binary from scratch. Deliverable Place your implementation under /app/submission/. Provide an executable shell script /app/submission/compile.sh that, when invoked with the working directory set to /app…

Excerpt only; not a complete executable task specification. Task ID task_ad9bf846cf814e6f · 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)0/5 · 0.0% [0.0%, 43.4%]0 / 50
GOOD_FAILURE: 0
BAD_FAILURE: 0
GOOD_SUCCESS: 0
BAD_SUCCESS: 0

Legacy evidence

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

Difficulty, with uncertainty

Selected-best difficulty: 100.0% [56.6%, 100.0%]. 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

5 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_8093682e803e4267
Claude Opus 5 · default (unverified)		Oct 9, 2026
console		0 · validNo diagnostic label
derived		Tokens: 172,660
Turns: 77
Cost: $12.3401		Not publicly available
trial_04448fde68184c5c
Claude Opus 5 · default (unverified)		Oct 9, 2026
console		0 · validNo diagnostic label
derived		Tokens: 226,815
Turns: 67
Cost: $12.1305		Not publicly available
trial_19fd638cc03540e5
Claude Opus 5 · default (unverified)		Oct 9, 2026
console		0 · validNo diagnostic label
derived		Tokens: 158,550
Turns: 45
Cost: $8.7053		Not publicly available
trial_b7f81bb934fa4e8e
Claude Opus 5 · default (unverified)		Oct 9, 2026
console		0 · validNo diagnostic label
derived		Tokens: 195,997
Turns: 69
Cost: $12.2760		Not publicly available
trial_ed7f5d2f7fff4f4c
Claude Opus 5 · default (unverified)		Oct 9, 2026
console		0 · validNo diagnostic label
derived		Tokens: 203,523
Turns: 68
Cost: $12.7788		Not publicly available