← polyphony · eval · dracula · ci
polyphony · gemini-2.5-flash
✗ fail↓ regression 60% → 33%Pass rate
33%
Cases
3 (2 failed)
Mode
eval
Suite
dracula
Env
ci
Started
2026-08-24 07:37 UTC
Duration
—
Cost
—
Tokens in/out
— / —
Commit
—
Branch
—
Source
—
Labels
| legacy_env | ci-dracula |
Compared with the previous run
Baseline 2026-08-17 07:21 UTC · 60% → this run 33%
cases added / removed
- − eval:continuity
- − eval:prose
Cases (3, 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:retrievalscore 0.82✓ pass
Output
precision@k=0.8182 mrr=0.9545