Daily test results · Cursor · effort medium
Is Grok 4.7 getting worse?
No verdict yet: day 1 of a 14-day baseline.
- Runs through
- Cursor
- Effort
- medium
- Provider
- cursor-cli
- Model id
grok-4.7-medium- 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 Grok 4.7 nerfed?
No verdict yet
This is day 1 of the 14-day baseline for Grok 4.7. The baseline began on 4 October 2026. If the model runs every day, the baseline is complete on 17 October 2026 and the first verdict is expected on 18 October 2026.
It is too early to say either way. Until the baseline is complete there is nothing to compare a new day with, and a single day moves by chance.
- Rating
- 1645±200 · one standard error
- Change since day 1
- –needs two days
- Pass rate
- 100%latest day · 3 graded tasks
- Days of data
- 1since 4 October 2026
What the runs took
- Median time per task
- 8m 32smean 7m 21s · 0 timeouts
- Output tokens per task
- 28k– thinking · 3.36M in
- Output tokens per second
- 63median · mean 63
- 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 3 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 |
|---|---|
| Grok 4.7 | 100%7m 21s28k |
Day by day
| Day | Rating | Passed | Timeouts | Time spent | Median time | Output tokens | Output tokens / s | Est. cost |
|---|---|---|---|---|---|---|---|---|
| 4 Oct | 1645 ±200 | 3/3 | 0 | 22m 04s | 8m 32s | 83k | 63 | – |
How this is measured
Grok 4.7 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.