run-0100
capability
citable URL: https://halobench.com/records/run-0100/ — this address never moves; the anchor /records/#run-0100 keeps resolving
date 2026-08-09 · window 2026-08-09T21:05:52Z → 2026-08-10T01:40:06Z
suite tau2-bench-airline@668d3bc · config cfg-0025
depth 32,768 tokens · scoring deterministic
Metrics
| metric | value |
|---|---|
| tasks_passed | 12 |
| tasks_total | 22 |
| mean_score | 0.5455 |
turns: total 482 · median 22 · p90 30 · max 36 — machine-written trailer, parsed at build time
Guard chain
not a performance run — no guard required
Per-task trace — the full record, no truncation
| task | reward | turns | seconds |
|---|---|---|---|
| 0 | 1 | 20 | 118 |
| 1 | 1 | 24 | 122 |
| 2 | 1 | 29 | 211 |
| 3 | 1 | 14 | 73 |
| 4 | 1 | 12 | 84 |
| 5 | 1 | 15 | 123 |
| 6 | 1 | 10 | 89 |
| 7 | 0 | 31 | 216 |
| 8 | 1 | 28 | 164 |
| 9 | 1 | 12 | 360 |
| 10 | 0 | 36 | 389 |
| 11 | 1 | 22 | 183 |
| 12 | 0 | 20 | 139 |
| 13 | 1 | 18 | 146 |
| 14 | 0 | 26 | 365 |
| 15 | 0 | 27 | 180 |
| 16 | 0 | 24 | 165 |
| 17 | 0 | 14 | 93 |
| 18 | 0 | 28 | 163 |
| 19 | 1 | 22 | 91 |
| 20 | 0 | 20 | 142 |
| 21 | 0 | 30 | 149 |
reward null = infrastructure error, excluded from every paired computation