Skip to content
evalship Get started →

evalship-hq / ponytail

Public

hardware calibration | ponytail

Ponytail behavior gates: hardware calibration, requested explanation, one runnable check. / hardware calibration | ponytail

Score on main

Oct 29: 0.67Oct 29: 0.00Oct 29: 1.00Oct 29: 1.00
Oct 29min 0.00, max 1.00Oct 29: 1.00

Last 4 runs

Stable across recent runs.

Recent results

CommitResultScoreDurationMetadata
7beb065 6 days ago Pass 1.00 26.1s provider: openrouter:anthropic/claude-opus-4.8, assertions: ["javascript"], judge: deterministic, repeats: 3/3 passed
545983b 6 days ago Pass 1.00 30.7s provider: openrouter:anthropic/claude-opus-4.8, assertions: ["javascript"], judge: deterministic, repeats: 3/3 passed
7e38f14 6 days ago Fail 0.00 35.5s provider: openrouter:anthropic/claude-opus-4.8, assertions: ["javascript"], judge: deterministic, repeats: 0/3 passed
c01cd19 6 days ago Pass 0.67 32.7s provider: openrouter:anthropic/claude-opus-4.8, assertions: ["javascript"], judge: deterministic, repeats: 2/3 passed