Leaderboard / anthropic/claude-fable-5
claude-fable-5
anthropic · Tasks passed 90.4% · Finance Index 92.2
Tasks passed
90.4%
Overall accuracy
88.1%
Finance Index
92.2
Consistency
2.6/3 avg
Est. eval cost
$1.95
Median latency
6.1s
Median output speed
1 tok/s
- Harness version
- 0.2.0
- Task set
- v2
- Runs per task
- 3
- Evaluated
- 7/6/2026, 10:00:22 AM
- Run ID
- c81ce016-ff75-41b5-9a53-53fbee374762
- Results file
- Download JSON
Pass@1 by Difficulty
Easy
—
Medium
—
Hard
—
Scores by domain
Tasks passed (%) · top 1 models
Quant
Per-attempt drill-down requires a local result JSON in `results/`. Aggregate scores are shown from the published leaderboard.