All configurations / model
Fable 5
- Configuration
- Fable 5 with no tools and no skill; the floor.
- Source
- claude-fable-5
- Recorded runs
- 700 scored outputs · $16.09 measured model spend · runs on 2026-08-31
- Access
- closed-API model · no tools
FIG. 01
By dimension
Scores /10 · Paired p-values are exploratory and unadjustedvoidVerify
Serving failuren=300 · verdict accuracy · evidence in hand · $0.0167/task · 2026-08-31
two of every three calls returned zero output tokens; a serving failure, not a score
Run provenance
Report path: outputs/scifact/results_matrix_fable5.json
Task pack: scifact-dev-300
Run: matrix-fable-5
- from memoryvoid · n=300 · $0.0169 · 2026-08-31 · two of every three calls returned zero output tokens; a serving failure, not a score
—Ground
Not yet tested.
—Find
Not yet tested.
4.69Extract
Baselinen=100 · mean(entity F1, relation F1) · $0.0602/task · 2026-08-31
entity F1 0.586, relation F1 0.352
Run provenance
Report path: outputs/extract/results.json
Task pack: scierc-test-100
Run: extract-100
—Analyze
Not yet tested.
—Compute
Not yet tested.
—Synthesize
Not yet tested.
—Review
Not yet tested.
—Hypothesize
Not yet tested.