Leaderboard / deepseek/deepseek-reasoner
deepseek-reasoner
deepseek · Tasks passed 84.9% · Finance Index 84.4
Tasks passed
84.9%
Overall accuracy
79.5%
Finance Index
84.4
Consistency
2.4/3 avg
Est. eval cost
$0.02
Median latency
—
Median output speed
—
- Harness version
- 0.1.0
- Task set
- v2
- Runs per task
- 3
- Evaluated
- 6/15/2026, 10:43:31 AM
- Run ID
- c34f1f99-0d05-4bd6-b995-6e3a3bab1baa
- 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.