← polyphony · eval · dracula · ci
polyphony · gemini-2.5-flash
✗ failPass rate
86%
Cases
7 (1 failed)
Mode
eval
Suite
dracula
Env
ci
Started
2026-07-14 07:24 UTC
Duration
—
Cost
—
Tokens in/out
— / —
Commit
—
Branch
—
Source
—
Labels
| legacy_env | ci-dracula |
Compared with the previous run
Baseline 2026-07-14 02:32 UTC · 67% → this run 86%
✓ newly passing · 1
- eval:ingestion
cases added / removed
- + eval:attribution
- + eval:continuity
- + eval:outline
- + eval:prose
Cases (7, 1 failed, failures first)
eval:attributionscore 0.33✗ fail
Output
accuracy=0.3333 chance=0.3333 n=3
eval:continuityscore 1.00✓ pass
Output
detection_recall=1.0 fpr=1.0
eval:extractionscore 0.71✓ pass
Output
F1=0.7059 P=0.6 R=0.8571 predicted=['Aldous Kerr', 'Nora', 'Percy', 'Mr. Boone', 'Dr. Ward', 'Sister Agatha', 'Renwick', 'Cora', 'Verhoeven', 'Elias']
eval:ingestionscore 0.90✓ pass
Output
grounded=9/10 avg_chunks=21.5
eval:outlinescore 0.90✓ pass
Output
nodes=6 structural_ok=True
⚖︎ Judge rationale
recovered score from unstructured reply
eval:prosescore 0.90✓ pass
Output
words=691
⚖︎ Judge rationale
The response effectively dramatizes the requested beat, is coherent and readable, and the two characters have distinct voices, although some sentences are overly elaborate and verbose, slightly detracting from the overall clarity.
eval:retrievalscore 0.82✓ pass
Output
precision@k=0.8182 mrr=0.9545