Tracer
← polyphony · eval · frankenstein · ci

polyphony · gemini-2.5-flash

✗ fail
Pass rate
50%
Cases
4 (2 failed)
Mode
eval
Suite
frankenstein
Env
ci
Started
2026-10-12 15:49 UTC
Duration
—
Cost
—
Tokens in/out
— / —
Commit
—
Branch
—
Source
—

Labels

legacy_envci-frankenstein

Compared with the previous run

Baseline 2026-10-05 15:08 UTC · 33% → this run 50%

cases added / removed
  • + eval:continuity

Cases (4, 2 failed, failures first)

eval:extractionscore 0.00✗ fail
Output
F1=0.0 P=0.0 R=0.0 predicted=[]
eval:ingestionscore 0.00✗ fail
Output
grounded=None/0 avg_chunks=None
eval:continuityscore 1.00✓ pass
Output
detection_recall=1.0 fpr=0.5
eval:retrievalscore 0.81✓ pass
Output
precision@k=0.8148 mrr=0.8333