All runs¶
Every published run, newest first. Each row is one sandbox version, on one host, under one profile, measured against one corpus version and judged under one version of the verdicts. How rows can be compared is in the methodology.
The counts are per result; other is needs-feature,
not-applicable and the lab faults. Each run's folder has its README, the comparison table
and the raw evidence of every case: the date links to it.
| run | sandbox | version | host | corpus | verdicts | contained | escaped | control-broke | unsupported | vacuous | other |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 2026-10-26 | tartaros | 0.1.0-alpha.16 | Ubuntu 24.04, 6.8.0 | v1.0 | 1.0-draft | 168 | 3 | 0 | 0 | 10 | 13 |
| 2026-10-26 | sandbox-runtime | 0.0.81 | Ubuntu 24.04, 6.8.0 | v1.0 (6 of 194) | 1.0-draft | 6 | 0 | 0 | 0 | 0 | 0 |
| 2026-10-22 | tartaros | 0.1.0-alpha.11 | Ubuntu 24.04, 6.8.0 | pre-1.0 | 1.0-draft | 162 | 3 | 0 | 0 | 10 | 13 |
| 2026-10-22 | tartaros | 0.1.0-alpha.10 | Ubuntu 24.04, 6.8.0 | pre-1.0 | 1.0-draft | 150 | 3 | 0 | 13 | 9 | 13 |
| 2026-10-21 | sandbox-runtime | 0.0.81 | Ubuntu 24.04, 6.8.0 | pre-1.0 | 1.0-draft | 133 | 14 | 1 | 18 | 9 | 13 |
| 2026-10-21 | nono | 0.80.0 | Ubuntu 24.04, 6.8.0 | pre-1.0 | 1.0-draft | 50 | 37 | 5 | 75 | 8 | 13 |
| 2026-10-21 | landrun | 0.1.17 | Ubuntu 24.04, 6.8.0 | pre-1.0 | 1.0-draft | 41 | 42 | 1 | 83 | 7 | 14 |
| 2026-10-21 | codex | 0.163.0 | Ubuntu 24.04, 6.8.0 | pre-1.0 | 1.0-draft | 95 | 24 | 29 | 18 | 9 | 13 |
| 2026-10-17 | landrun | 0.1.17 | Ubuntu 24.04, 6.8.0 | pre-1.0 | 1.0-draft | 41 | 42 | 1 | 83 | 7 | 14 |
| 2026-10-16 | sandbox-runtime | 0.0.79 | Ubuntu 24.04, 6.8.0 | pre-1.0 | 1.0-draft | 124 | 21 | 3 | 18 | 9 | 13 |
| 2026-10-16 | nono | 0.80.0 | Ubuntu 24.04, 6.8.0 | pre-1.0 | 1.0-draft | 50 | 37 | 5 | 75 | 8 | 13 |
| 2026-10-16 | landrun | 0.1.17 | Ubuntu 24.04, 6.8.0 | pre-1.0 | 1.0-draft | 24 | 38 | 1 | 105 | 6 | 14 |
| 2026-10-16 | codex | 0.162.1 | Ubuntu 24.04, 6.8.0 | pre-1.0 | 1.0-draft | 95 | 24 | 29 | 18 | 9 | 13 |
| 2026-10-15 | sandbox-runtime | 0.0.79 | Ubuntu 24.04, 6.8.0 | pre-1.0 | v0 | 120 | 22 | 4 | 18 | 9 | 13 |
| 2026-10-15 | nono | 0.80.0 | Ubuntu 24.04, 6.8.0 | pre-1.0 | v0 | 48 | 37 | 6 | 74 | 8 | 13 |
| 2026-10-15 | landrun | 0.1.17 | Ubuntu 24.04, 6.8.0 | pre-1.0 | v0 | 22 | 38 | 2 | 104 | 6 | 14 |
| 2026-10-15 | codex | 0.162.1 | Ubuntu 24.04, 6.8.0 | pre-1.0 | v0 | 92 | 24 | 30 | 18 | 9 | 13 |
| 2026-10-15 | sandbox-runtime | 0.0.79 | Ubuntu 24.04, 6.8.0 | pre-1.0 | v0 | 21 | 0 | 0 | 0 | 1 | 0 |
| 2026-10-15 | nono | 0.80.0 | Ubuntu 24.04, 6.8.0 | pre-1.0 | v0 | 17 | 4 | 0 | 0 | 1 | 0 |
| 2026-10-15 | codex | 0.162.1 | Ubuntu 24.04, 6.8.0 | pre-1.0 | v0 | 18 | 0 | 3 | 0 | 1 | 0 |
| 2026-10-15 | sandbox-runtime | 0.0.79 | Ubuntu 24.04, 6.8.0 | pre-1.0 | v0 | 99 | 22 | 4 | 18 | 8 | 13 |
| 2026-10-15 | nono | 0.80.0 | Ubuntu 24.04, 6.8.0 | pre-1.0 | v0 | 31 | 33 | 6 | 74 | 7 | 13 |
| 2026-10-15 | codex | 0.162.1 | Ubuntu 24.04, 6.8.0 | pre-1.0 | v0 | 74 | 24 | 27 | 18 | 8 | 13 |
pre-1.0: the run ran contracts that changed before the corpus was versioned. Its results stand as published, and What changed by version compares runs on the contracts they share unchanged.