Cowork benchmark scoreboard
vs harness-delta baseline — Cowork anchor: no anchor yet
Headline uncapped R
Unavailable
No canonical 8-scenario × 2-arm weekly run
Cowork anchor
No Cowork anchor yet. The versioned Phase 6 quality-only anchor boundary is reserved; no manual result is inferred from automated arms.
Partial run 9d4544417c65. cwb-01 was skipped because the fixture environment was unset; cwb-05–cwb-08 are void after the spend limit, with 24 DNFs. These dispositions remain visible and are not concealed or converted to successful scores.
No scoped alerts. Expected baseline-favored long-document cost/latency does not alert.
Weekly trend
| Week | Run | Date | Uncapped R | North model | Metric |
|---|---|---|---|---|---|
| No eligible weekly runs. | |||||
Pool split
No canonical weekly run is available.
Per-dimension utilities and uncapped ratios
| Dimension | North mean | Baseline mean | Uncapped ratio |
|---|---|---|---|
| No paired weekly data. | |||
Per-scenario results
| Scenario | Pool | North Q | Baseline Q | Uncapped R | Dispositions |
|---|---|---|---|---|---|
| No canonical weekly data. | |||||
DNF / unscored / skipped log
| Run | Scenario | Arm | Status | Count | Reason |
|---|---|---|---|---|---|
4ae3727b60e9 | cwb-05 | north | DNF | 1 | error |
4dd9374bf25e | cwb-07 | baseline | DNF | 1 | error |
5b61b841c49e | cwb-07 | baseline | Unscored | 1 | completeness:utility: utility must be 1 exactly when missingRequirements is empty |
6489c1d930d4 | cwb-07 | baseline | DNF | 1 | error |
9d4544417c65 | cwb-02 | baseline | Unscored | 1 | completeness:utility: utility must be 1 exactly when missingRequirements is empty |
9d4544417c65 | cwb-02 | north | Unscored | 1 | completeness:utility: utility must be 1 exactly when missingRequirements is empty |
9d4544417c65 | cwb-04 | baseline | Unscored | 1 | conciseness:preambleEnd: must be within rendered finalText |
9d4544417c65 | cwb-04 | north | Unscored | 2 | completeness:utility: utility must be 1 exactly when missingRequirements is empty |
a88921605c5c | cwb-01 | baseline | Unscored | 1 | completeness:utility: utility must be 1 exactly when missingRequirements is empty |
a88921605c5c | cwb-01 | north | Unscored | 1 | completeness:utility: utility must be 1 exactly when missingRequirements is empty |
ae3458532b2e | cwb-08 | baseline | Unscored | 1 | completeness:utility: utility must be 1 exactly when missingRequirements is empty |
ae3458532b2e | cwb-08 | north | Unscored | 1 | completeness:utility: utility must be 1 exactly when missingRequirements is empty |
Partial and diagnostic runs
Runs without the canonical 8 scenarios × 2 arms × k unique attempt keys are shown here but excluded from weekly trend and consecutive-run alerts.
| Run | Timestamp | Records | Dispositions |
|---|---|---|---|
9d4544417c65 | 2026-07-11T03:14:50.260Z | 18 | scored 13 · DNF 0 · unscored 5 · skipped 0 |
6489c1d930d4 | 2026-07-11T04:27:52.008Z | 1 | scored 0 · DNF 1 · unscored 0 · skipped 0 |
4dd9374bf25e | 2026-07-11T04:29:19.825Z | 1 | scored 0 · DNF 1 · unscored 0 · skipped 0 |
26070c61821c | 2026-07-11T08:35:34.593Z | 6 | scored 6 · DNF 0 · unscored 0 · skipped 0 |
5b61b841c49e | 2026-07-11T08:43:05.279Z | 6 | scored 5 · DNF 0 · unscored 1 · skipped 0 |
ae3458532b2e | 2026-07-11T08:46:35.239Z | 6 | scored 4 · DNF 0 · unscored 2 · skipped 0 |
4ae3727b60e9 | 2026-07-11T08:50:21.712Z | 1 | scored 0 · DNF 1 · unscored 0 · skipped 0 |
a88921605c5c | 2026-07-11T09:15:40.242Z | 6 | scored 4 · DNF 0 · unscored 2 · skipped 0 |