Task gallery / Machine learning / Version 1
Task evidence / repo
equity-rare-strata-memo
legacy-onlyChosen benchmark version- Reference solution (oracle)
- Pass
- No-op resistance check
- Pass
- QA verdict
- snorkel review: needs-revision x2
- Aggregate eligibility
- Eligible version
The task
An instruction excerpt is not available in the public snapshot.
Excerpt only; not a complete executable task specification. Task ID review-50844bdc0b32f0b9 · 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) | 6/10 · 60.0% [31.3%, 83.2%] | 0 / 10 | 0 | GOOD_FAILURE: 0 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0 |
| GPT-5.5 · default (unverified) | 2/10 · 20.0% [5.7%, 51.0%] | 0 / 10 | 0 | GOOD_FAILURE: 0 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0 |
Every recorded run
28 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__ug6eUXzoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__sA5V4MUnop@@ | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__nW8jkvooracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__EC58gU2oracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__X7gwBJoClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 12,330 Turns: — Cost: $0.7083 | Not publicly available |
tbench-task__KpQyKj4Claude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 12,759 Turns: — Cost: $0.7548 | Not publicly available |
tbench-task__y9XgzyVClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 15,020 Turns: — Cost: $0.8907 | Not publicly available |
tbench-task__n89YSVXClaude Opus 4.8 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 12,647 Turns: — Cost: $0.7412 | Not publicly available |
tbench-task__gSBBnr6Claude Opus 4.8 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 12,631 Turns: — Cost: $0.7295 | Not publicly available |
tbench-task__NjanUBaGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 6,099 Turns: — Cost: $0.7874 | Not publicly available |
tbench-task__EbVQ5VnGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 7,504 Turns: — Cost: $0.8582 | Not publicly available |
tbench-task__3SJufDqGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 8,364 Turns: — Cost: $0.9981 | Not publicly available |
tbench-task__AuefCmcGPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 6,269 Turns: — Cost: $0.8524 | Not publicly available |
tbench-task__tAgoDjuGPT-5.5 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 8,641 Turns: — Cost: $1.1310 | Not publicly available |
tbench-task__eCfxVu2nop@@ | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__jee6UYRoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__fbTMCnaoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__72mbLKhoracle@@ | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: — Turns: — Cost: — | Not publicly available |
tbench-task__jWiw9cuClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 12,569 Turns: — Cost: $0.7433 | Not publicly available |
tbench-task__K57kMbQClaude Opus 4.8 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 13,555 Turns: — Cost: $0.8012 | Not publicly available |
tbench-task__aLu5mxPClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 14,206 Turns: — Cost: $0.8822 | Not publicly available |
tbench-task__avk5v4rClaude Opus 4.8 · default (unverified) | Not recorded repo | 1 · valid | No diagnostic label derived | Tokens: 12,702 Turns: — Cost: $0.7343 | Not publicly available |
tbench-task__dy7UPEnClaude Opus 4.8 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 12,170 Turns: — Cost: $0.6550 | Not publicly available |
tbench-task__fp9HBZBGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 6,622 Turns: — Cost: $0.9206 | Not publicly available |
tbench-task__w9KqTVcGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 7,132 Turns: — Cost: $1.0878 | Not publicly available |
tbench-task__TRqhxfCGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 5,725 Turns: — Cost: $0.7947 | Not publicly available |
tbench-task__CmR8u64GPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 7,527 Turns: — Cost: $1.1135 | Not publicly available |
tbench-task__HYWzeEsGPT-5.5 · default (unverified) | Not recorded repo | 0 · valid | No diagnostic label derived | Tokens: 7,808 Turns: — Cost: $0.9955 | Not publicly available |