Daily test results · Kimi Code · effort default
Is Kimi K3 getting worse?
No verdict yet: it has not had its first run.
- Runs through
- Kimi Code
- Effort
- default
- Provider
- kimi-cli
- Model id
kimi-code/k3- Tasks
- New issues in real code
- Updated
- 2026-10-04 20:40 UTC
Rating over time
Higher is better. The band is one standard error either side. The dashed line is the first day. Movement inside the band means nothing.
Was Kimi K3 nerfed?
No verdict yet
Kimi K3 has not had its first run. There is no data, so there is nothing to say either way.
A verdict needs 14 days of this model's own results first, and then at least one newer day to compare with them.
- Rating
- –no runs yet
- Change since day 1
- –needs two days
- Pass rate
- –no runs yet
- Days of data
- 0waiting for first run
What the runs took
- Median time per task
- –mean – · 0 timeouts
- Output tokens per task
- –– thinking · – in
- Output tokens per second
- –median · mean –
- Estimated cost per task
- –price not set
Estimated cost is tokens at API list prices, not money spent. A dash means no list price is set. Numbers cover 0 graded tasks over 1 day.
Time per task
How long each task took. A task not finished in 15 minutes is a fail, and counts as 15 minutes of time spent.
By task family
Pass rate, mean time and mean output tokens for each kind of problem.
| Model | pull-request |
|---|---|
| Kimi K3 | ––– |
Day by day
| Day | Rating | Passed | Timeouts | Time spent | Median time | Output tokens | Output tokens / s | Est. cost |
|---|---|---|---|---|---|---|---|---|
| 4 Oct | No graded tasks | 0/0 | 0 | 0.0s | – | 0 | – | – |
How this is measured
Kimi K3 gets the same new tasks as every other model. Each task is an issue in a large, working codebase, and the model writes the change that resolves it with its own coding tool, as it would for a pull request. A program runs the tests to check the change. No task is ever sent twice to the same model, so there is nothing to memorise.
The model is compared with itself: the last 7 days against its first 14 days. A verdict is only given when the difference is too large to be chance. A task not finished in 15 minutes counts as a fail.
Not a leaderboard. Models run at different effort settings and through different tools.