Leaderboard / moonshot/kimi-k3
kimi-k3
moonshot · Tasks passed 89.0% · Finance Index 87.2
Tasks passed
89.0%
Overall accuracy
86.3%
Finance Index
87.2
Consistency
2.6/3 avg
Est. eval cost
$3.13
Median latency
18.2s
Median output speed
25 tok/s
- Harness version
- 0.2.0
- Task set
- v2
- Runs per task
- 3
- Evaluated
- 7/23/2026, 6:50:54 AM
- Run ID
- 39ef3623-4763-4999-b666-6f9057f99327
- 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.