oci-layer-admission-audit
mediumCurrent calibratedChosen benchmark version- Reference solution (oracle)
- Pass
- No-op resistance check
- Pass
- QA verdict
- Not recorded
- Aggregate eligibility
- Eligible version
The task
Excerpt only; not a complete executable task specification. Task ID task_db1402fc696e4530 · 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 |
|---|---|---|---|---|
| Tencent HY4 (preview) · think | 3/5 · 60.0% [23.1%, 88.2%] | 5 / 5 | 0 | GOOD_FAILURE: 2 BAD_FAILURE: 0 GOOD_SUCCESS: 3 BAD_SUCCESS: 0 |
| Claude Opus 5 · xhigh | 0/1 | 1 / 1 | 0 | GOOD_FAILURE: 1 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0 |
Legacy evidence
| Model / effort | Verifier result [95% Wilson] | Diagnostic labels / valid | HARNESS_ERROR · excluded | Outcome classes |
|---|
Difficulty, with uncertainty
Selected-best difficulty: 40.0% [11.8%, 76.9%]. 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
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_e0baa6739078437bclaude-opus-4-8@@xhigh | Oct 21, 2026 console | No reward · excludedno_reward | HARNESS_ERROR derived | Tokens: — Turns: 27 Cost: — | Not publicly available |
trial_d1c88a9fca494fe3Tencent HY4 (preview) · think | Oct 21, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 75,549 Turns: 55 Cost: $4.5268 | Not publicly available |
trial_7aab29cfef824866Claude Opus 5 · xhigh | Oct 21, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 102,565 Turns: 43 Cost: $4.9714 | Not publicly available |
trial_d4cba0f662f04734Tencent HY4 (preview) · think | Oct 21, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 82,996 Turns: 71 Cost: $5.7585 | Not publicly available |
trial_12429279214744adTencent HY4 (preview) · think | Oct 21, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 76,543 Turns: 36 Cost: $3.6922 | Not publicly available |
trial_6ea7420f4b9749a7Tencent HY4 (preview) · think | Oct 21, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 75,839 Turns: 50 Cost: $4.4309 | Not publicly available |
trial_de7b1b3dfced4b20Tencent HY4 (preview) · think | Oct 21, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 82,653 Turns: 63 Cost: $5.2353 | Not publicly available |
oci-layer-admission-audit-oracle-1-6f962cb0oracle@@ | Oct 21, 2026 delivery | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
oci-layer-admission-audit-nop-25b124b4nop@@ | Oct 21, 2026 delivery | 0 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
oci-layer-admission-audit-oracle-2-09ac1ef0oracle@@ | Oct 21, 2026 delivery | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |