qdrant-fix-wrong-multivectors-count-in-s
contested/defectiveCurrent calibratedOutside aggregate scope- Reference solution (oracle)
- Pass
- No-op resistance check
- Pass
- QA verdict
- deepswe review: OUT of delivery (coordinator, 2026-10-22 ~03:00Z): fails D2; rem
- 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 task_efac1df7688e4a98 · version 4. 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 |
|---|---|---|---|---|
| Claude Opus 5 · high | 5/5 · 100.0% [56.6%, 100.0%] | 5 / 5 | 0 | GOOD_FAILURE: 0 BAD_FAILURE: 0 GOOD_SUCCESS: 5 BAD_SUCCESS: 0 |
| Tencent HY4 (preview) · think | 3/8 · 37.5% [13.7%, 69.4%] | 8 / 8 | 0 | GOOD_FAILURE: 5 BAD_FAILURE: 0 GOOD_SUCCESS: 3 BAD_SUCCESS: 0 |
Legacy evidence
| Model / effort | Verifier result [95% Wilson] | Diagnostic labels / valid | HARNESS_ERROR · excluded | Outcome classes |
|---|
Every recorded run
19 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_9047b93ceabe4659oracle@@ | Oct 22, 2026 console | 1 · valid | GOOD_SUCCESS frozen-classifier | Tokens: — Turns: — Cost: — | Not publicly available |
trial_dc55b7129b5b464anop@@ | Oct 22, 2026 console | 0 · valid | GOOD_FAILURE frozen-classifier | Tokens: — Turns: — Cost: — | Not publicly available |
trial_287e9d2b65404846Claude Opus 5 · high | Oct 22, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 112,568 Turns: 137 Cost: $16.7012 | Not publicly available |
trial_72f9ab2cb0d74d8cClaude Opus 5 · high | Oct 22, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 58,338 Turns: 102 Cost: $7.5345 | Not publicly available |
trial_7439e81bd7614e73Claude Opus 5 · high | Oct 22, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 130,743 Turns: 155 Cost: $19.8686 | Not publicly available |
trial_b650b87f62554494Claude Opus 5 · high | Oct 22, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 78,977 Turns: 121 Cost: $12.0364 | Not publicly available |
trial_b9bc13200e4a4b78Claude Opus 5 · high | Oct 22, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 69,384 Turns: 114 Cost: $9.1153 | Not publicly available |
trial_2831f448cd7644e5Tencent HY4 (preview) · think | Oct 22, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 124,380 Turns: 229 Cost: $18.8626 | Not publicly available |
trial_2d83bb7583fc4ffcTencent HY4 (preview) · think | Oct 22, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 188,887 Turns: 150 Cost: $16.6602 | Not publicly available |
trial_44a6534974da4565Tencent HY4 (preview) · think | Oct 22, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 308,934 Turns: 185 Cost: $25.1564 | Not publicly available |
trial_6e7f0be501904205tencent/hy4-preview@@ | Oct 22, 2026 console | No reward · excludedno_reward | No diagnostic label No diagnostic source | Tokens: — Turns: — Cost: — | Not publicly available |
trial_72c130b67d1d4d92Tencent HY4 (preview) · think | Oct 22, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 312,605 Turns: 138 Cost: $34.4860 | Not publicly available |
trial_7da419046d2c4754tencent/hy4-preview@@ | Oct 22, 2026 console | No reward · excludedno_reward | No diagnostic label No diagnostic source | Tokens: — Turns: — Cost: — | Not publicly available |
trial_7dbe736393334ad2tencent/hy4-preview@@ | Oct 22, 2026 console | No reward · excludedno_reward | No diagnostic label No diagnostic source | Tokens: — Turns: — Cost: — | Not publicly available |
trial_f5d281eb586c40cdtencent/hy4-preview@@ | Oct 22, 2026 console | No reward · excludedno_reward | No diagnostic label No diagnostic source | Tokens: — Turns: — Cost: — | Not publicly available |
trial_2a8726307b3b4cf7Tencent HY4 (preview) · think | Oct 22, 2026 console | 0 · valid | GOOD_FAILURE independent-review | Tokens: 243,999 Turns: 190 Cost: $23.2637 | Not publicly available |
trial_3455aa6e2b504257Tencent HY4 (preview) · think | Oct 22, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 134,920 Turns: 190 Cost: $15.7186 | Not publicly available |
trial_74cde23298e1452aTencent HY4 (preview) · think | Oct 22, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 179,353 Turns: 119 Cost: $22.0880 | Not publicly available |
trial_cb8b7b36a2034466Tencent HY4 (preview) · think | Oct 22, 2026 console | 1 · valid | GOOD_SUCCESS independent-review | Tokens: 190,875 Turns: 143 Cost: $23.9885 | Not publicly available |