Model detail
Claude Fable 5
Provider: Anthropic · Public slug: claude-fable-5
- Rank
- 1
- Rank movement
- Baseline
- Score
- 71.8
- Last measured
- 2026-07-05
- Coverage
- None not supported
Reasoning scores
- XHigh
- 73.7
- Medium
- 69.8
- None
- —
Generation health
XHigh63%37%0%n 8Medium88%0%12%n 8 None not supportedCost summary
- Mean standard list-price equivalent
- $1.04
- Median unique-cell cost
- $0.88
- Unique-cell range
- $0.33–$1.92
- Coverage
- 16 unique cells / 16 observed runs
- Observed-run total
- $16.70
- Evidence basis
- Standard list-price estimate
- Mean output
- 18k tok
- Output range
- 4.3k–36k tok
- Token samples
- 16
Cost means equal-weight unique model/game/reasoning cells. Provider-account billed spend is reported separately on Charts.
Run setup
- Overall Models: combines public reasoning variants
- Standard GameBench code-generation prompt