Task gallery / Security / cyber / Version 1
Reference solution (oracle)
Unverified
No-op resistance check
Unverified
QA verdict
EXCLUDE
Aggregate eligibility
Excluded / other version
Quality exclusion
  • Known task defect recorded
  • Task fault on at least half of labelled current-model failures

These per-version observations remain visible, but this version does not contribute to aggregate pass rates.

The task

An instruction excerpt is not available in the public snapshot.

Excerpt only; not a complete executable task specification. Task ID task_4faf88d8421f4bf7 · version 1. Selection status: known curated delivery cohort.

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 · high3/5 · 60.0% [23.1%, 88.2%]5 / 50
GOOD_FAILURE: 1
BAD_FAILURE: 1
GOOD_SUCCESS: 3
BAD_SUCCESS: 0
Tencent HY4 (preview) · think3/8 · 37.5% [13.7%, 69.4%]8 / 80
GOOD_FAILURE: 2
BAD_FAILURE: 3
GOOD_SUCCESS: 3
BAD_SUCCESS: 0

Legacy evidence

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

Every recorded run

13 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_3f53090604ec4026
Claude Opus 5 · high
Oct 22, 2026
delivery
0 · validBAD_FAILURE
independent-review
Tokens: —
Turns: 20
Cost: —
Not publicly available
trial_440d4f89a0dc4287
Claude Opus 5 · high
Oct 22, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 20
Cost: —
Not publicly available
trial_979d62f4ec5444fc
Claude Opus 5 · high
Oct 22, 2026
delivery
1 · validGOOD_SUCCESS
independent-review
Tokens: —
Turns: 23
Cost: —
Not publicly available
trial_d7566a99572445ed
Claude Opus 5 · high
Oct 22, 2026
delivery
1 · validGOOD_SUCCESS
independent-review
Tokens: —
Turns: 23
Cost: —
Not publicly available
trial_ecf044c7ede8452a
Claude Opus 5 · high
Oct 22, 2026
delivery
1 · validGOOD_SUCCESS
independent-review
Tokens: —
Turns: 22
Cost: —
Not publicly available
trial_09718e36332b4b76
Tencent HY4 (preview) · think
Oct 21, 2026
delivery
0 · validBAD_FAILURE
independent-review
Tokens: —
Turns: 38
Cost: —
Not publicly available
trial_098b437ae6164de9
Tencent HY4 (preview) · think
Oct 21, 2026
delivery
0 · validBAD_FAILURE
independent-review
Tokens: —
Turns: 21
Cost: —
Not publicly available
trial_38b78adfceb647e1
Tencent HY4 (preview) · think
Oct 21, 2026
delivery
1 · validGOOD_SUCCESS
independent-review
Tokens: —
Turns: 28
Cost: —
Not publicly available
trial_6d9f53d781a14300
Tencent HY4 (preview) · think
Oct 21, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 46
Cost: —
Not publicly available
trial_9812690361684090
Tencent HY4 (preview) · think
Oct 21, 2026
delivery
0 · validBAD_FAILURE
independent-review
Tokens: —
Turns: 32
Cost: —
Not publicly available
trial_dfe217d8f78748b5
Tencent HY4 (preview) · think
Oct 21, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 48
Cost: —
Not publicly available
trial_6c1f5650b5534104
Tencent HY4 (preview) · think
Oct 21, 2026
delivery
1 · validGOOD_SUCCESS
independent-review
Tokens: —
Turns: 30
Cost: —
Not publicly available
trial_54b32232380340e2
Tencent HY4 (preview) · think
Oct 22, 2026
delivery
1 · validGOOD_SUCCESS
independent-review
Tokens: —
Turns: 47
Cost: —
Not publicly available