tbrain-cohort-key-admission-r
contested/defectiveOutside aggregate scope- Reference solution (oracle)
- Pass
- No-op resistance check
- Pass
- QA verdict
- snorkel review: accept x1
- Aggregate eligibility
- Excluded / other version
- Known task defect recorded
These per-version observations remain visible, but this version does not contribute to aggregate pass rates.
The task
Excerpt only; not a complete executable task specification. Task ID review-cf636d6c0c0fed4f · 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 |
|---|
Legacy evidence
| Model / effort | Verifier result [95% Wilson] | Diagnostic labels / valid | HARNESS_ERROR · excluded | Outcome classes |
|---|---|---|---|---|
| GPT-5.5 · default (unverified) | 4/5 · 80.0% [37.6%, 96.4%] | 0 / 5 | 0 | GOOD_FAILURE: 0 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0 |
| Claude Opus 4.8 · default (unverified) | 1/2 | 0 / 2 | 3 | GOOD_FAILURE: 0 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0 |
Every recorded run
14 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 |
|---|---|---|---|---|---|
tbench-task__BqA3GNUnop@@ | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__o8qfvjVoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__ttXedBSoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__J8nEf6Loracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__2y8uXS7GPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 31,097 Turns: — Cost: $4.0149 | Not publicly available |
tbench-task__VkFT7QGGPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 37,911 Turns: — Cost: $4.8011 | Not publicly available |
tbench-task__JNXBdHCClaude Opus 4.8 · default (unverified) | Not recorded repo | 0 · excludedharness_error | HARNESS_ERROR derived | Tokens: 67,785 Turns: — Cost: $4.3552 | Not publicly available |
tbench-task__RYWiXkuGPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 20,524 Turns: — Cost: $2.6841 | Not publicly available |
tbench-task__mqZi74VClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · excludedharness_error | HARNESS_ERROR derived | Tokens: 48,748 Turns: — Cost: $3.6409 | Not publicly available |
tbench-task__5vPqA3XGPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 36,776 Turns: — Cost: $5.0762 | Not publicly available |
tbench-task__ae4y7HWClaude Opus 4.8 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 20,823 Turns: — Cost: $1.0997 | Not publicly available |
tbench-task__yuJB2hgClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · excludedharness_error | HARNESS_ERROR derived | Tokens: 30,489 Turns: — Cost: $2.1163 | Not publicly available |
tbench-task__p9NUhjwClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 41,082 Turns: — Cost: $2.5777 | Not publicly available |
tbench-task__dvyHkvNGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 32,102 Turns: — Cost: $4.7594 | Not publicly available |