polyphony · gemini-2.5-flash

Mode

eval

Env

ci-frankenstein

Pass rate

67%

Result

fail

Duration

—

Cost

—

Tokens in/out

— / —

Git SHA

Started

2026-07-20 09:42

Cases (6, failures first)

eval:attributionscore 0.33fail

Output

accuracy=0.3333 chance=0.3333 n=3

eval:prosescore 0.00fail

Output

words=0

⚖︎ Judge rationale

empty scene (terminal status=failed: generation failed, blocked, or quota-exhausted)

eval:continuityscore 1.00pass

Output

detection_recall=1.0 fpr=1.0

eval:extractionscore 0.59pass

Output

F1=0.5882 P=0.5 R=0.7143 predicted=['Mrs. Sarrow', 'Isolde', 'Uncle Thomas', 'Hollis Crane', 'Vandel', 'Cosima', 'Alina', 'Fenwick', 'The Creature', 'The Stranger']

eval:ingestionscore 0.63pass

Output

grounded=5/8 avg_chunks=5.62

eval:retrievalscore 0.85pass

Output

precision@k=0.8519 mrr=0.8704