Leaderboard / deepseek/deepseek-v4-flash
deepseek-v4-flash
deepseek · Tasks passed 93.2% · Finance Index 94.4
Tasks passed
93.2%
Overall accuracy
84.9%
Finance Index
94.4
Consistency
2.5/3 avg
Est. eval cost
$0.02
Median latency
14.4s
Median output speed
3 tok/s
- Harness version
- 0.2.0
- Task set
- v2
- Runs per task
- 3
- Evaluated
- 7/13/2026, 2:17:55 PM
- Run ID
- 7dcf50c3-917a-4845-b920-574bcae2c67c
- 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.