Leaderboard / anthropic/claude-haiku-4-5-20251001
claude-haiku-4-5-20251001
anthropic · Tasks passed 89.0% · Finance Index 82.8
Tasks passed
89.0%
Overall accuracy
85.8%
Finance Index
82.8
Consistency
2.6/3 avg
Est. eval cost
$0.78
Median latency
3.9s
Median output speed
103 tok/s
- Harness version
- 0.2.0
- Task set
- v2
- Runs per task
- 3
- Evaluated
- 7/16/2026, 8:34:15 AM
- Run ID
- ef5d836f-9856-4b48-812a-cd1162debdd9
- 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.