run-0102
capability
citable URL: https://halobench.com/records/run-0102/ — this address never moves; the anchor /records/#run-0102 keeps resolving
date 2026-08-10 · window 2026-08-10T09:07:30Z → 2026-08-10T14:22:34Z
suite tau2-bench-airline@668d3bc · config cfg-0027
depth 32,768 tokens · scoring deterministic
Metrics
| metric | value |
|---|---|
| tasks_passed | 10 |
| tasks_total | 16 |
| mean_score | 0.625 |
turns: total 530 · median 28 · p90 60 · max 84 — 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 | 24 | 199 |
| 1 | 1 | 36 | 191 |
| 2 | 0 | 84 | 538 |
| 3 | 1 | 16 | 94 |
| 4 | 1 | 38 | 265 |
| 5 | 1 | 24 | 206 |
| 6 | 1 | 18 | 242 |
| 7 | 0 | 22 | 143 |
| 8 | 1 | 28 | 238 |
| 9 | 1 | 24 | 204 |
| 10 | 0 | 26 | 492 |
| 11 | 0 | 30 | 388 |
| 12 | null (infrastructure) | 0 | — |
| 13 | 1 | 40 | 851 |
| 14 | 0 | 60 | 1030 |
| 15 | 0 | 28 | 391 |
| 16 | 1 | 32 | 438 |
reward null = infrastructure error, excluded from every paired computation
Cited by — computed at build time, never stored
model pages nemotron3-super