delayed-label-triage-pipeline
legacy-onlyChosen benchmark version- Reference solution (oracle)
- Pass
- No-op resistance check
- Pass
- QA verdict
- snorkel review: needs-revision x2, accept x1
- Aggregate eligibility
- Eligible version
The task
Excerpt only; not a complete executable task specification. Task ID review-51b8441e76d0691c · 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 |
|---|---|---|---|---|
| Claude Opus 4.8 · default (unverified) | 15/15 · 100.0% [79.6%, 100.0%] | 0 / 15 | 0 | GOOD_FAILURE: 0 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0 |
| GPT-5.5 · default (unverified) | 7/15 · 46.7% [24.8%, 69.9%] | 0 / 15 | 0 | GOOD_FAILURE: 0 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0 |
Every recorded run
42 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__WZBZinonop@@ | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__ES4MFUQoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__Ncf9BJ3oracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__Kr7DYNDoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__bPEi9vGClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 12,768 Turns: — Cost: $0.6855 | Not publicly available |
tbench-task__ogQYN7SClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 14,608 Turns: — Cost: $0.7283 | Not publicly available |
tbench-task__qthKr9vClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 13,283 Turns: — Cost: $0.6747 | Not publicly available |
tbench-task__Ng8E5puClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 13,954 Turns: — Cost: $0.8435 | Not publicly available |
tbench-task__DRpo6P2Claude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 16,532 Turns: — Cost: $0.9608 | Not publicly available |
tbench-task__hDYQ7voGPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 20,214 Turns: — Cost: $2.0312 | Not publicly available |
tbench-task__2qJzgM7GPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 15,154 Turns: — Cost: $1.2001 | Not publicly available |
tbench-task__enSCi2kGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 17,520 Turns: — Cost: $1.3480 | Not publicly available |
tbench-task__AS9Pyk5GPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 16,557 Turns: — Cost: $1.8177 | Not publicly available |
tbench-task__AntJ3pyGPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 19,778 Turns: — Cost: $1.8217 | Not publicly available |
tbench-task__Q4Q8Kwroracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__BPTtMuinop@@ | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__7aGnfgeoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__HtHxJcsoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__RBJncf2Claude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 12,118 Turns: — Cost: $0.6337 | Not publicly available |
tbench-task__6d3LFkDClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 17,884 Turns: — Cost: $1.0087 | Not publicly available |
tbench-task__RmhdaBFClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 13,243 Turns: — Cost: $0.6923 | Not publicly available |
tbench-task__A89mfG7Claude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 16,548 Turns: — Cost: $0.8880 | Not publicly available |
tbench-task__nnHm7WXClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 15,280 Turns: — Cost: $0.7865 | Not publicly available |
tbench-task__LEZhRRtGPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 27,093 Turns: — Cost: $2.5039 | Not publicly available |
tbench-task__mX7PbLSGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 26,802 Turns: — Cost: $2.7483 | Not publicly available |
tbench-task__TkeM9LLGPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 23,544 Turns: — Cost: $1.8832 | Not publicly available |
tbench-task__TJcKRAyGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 21,028 Turns: — Cost: $2.1103 | Not publicly available |
tbench-task__KBEvTLCGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 25,045 Turns: — Cost: $2.6074 | Not publicly available |
tbench-task__x6fqRuDoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__5hFS8ujoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__giTjtSknop@@ | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__BayM8LRoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__e4x6a9LClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 16,234 Turns: — Cost: $0.8984 | Not publicly available |
tbench-task__arJqXZoClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 11,514 Turns: — Cost: $0.5834 | Not publicly available |
tbench-task__JQbGkTYClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 16,283 Turns: — Cost: $0.8661 | Not publicly available |
tbench-task__nfetHsCClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 14,997 Turns: — Cost: $0.8595 | Not publicly available |
tbench-task__cwJ6T7dClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 17,996 Turns: — Cost: $0.9955 | Not publicly available |
tbench-task__MB8iRXgGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 24,230 Turns: — Cost: $2.6524 | Not publicly available |
tbench-task__6oBvv4fGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 29,846 Turns: — Cost: $2.8116 | Not publicly available |
tbench-task__CQ5qKa2GPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 16,182 Turns: — Cost: $1.6468 | Not publicly available |
tbench-task__zx83bbtGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 17,283 Turns: — Cost: $1.7706 | Not publicly available |
tbench-task__2Ef88bCGPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 26,500 Turns: — Cost: $2.4985 | Not publicly available |