xinxuxin /keystone-bench
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
- Stars
- 1,099 stars
- Forks
- 3 forks
- Language
- Python
- License
- OTHER
- Created
- Sep 7, 2026
- Last push
- Oct 19, 2026
- Updated
- Nov 2, 2026
- ai-safety
- benchmark
- clinical-decision-support
- dataset
- evaluation
- health
- healthbench
- large-language-models
- llm-evaluation
- medical-ai
Admitted to the Repository Index on Oct 23, 2026: +146 stars in 7 days.
Star History
56 days recorded, Sep 9, 2026 – Nov 3, 2026 (UTC). Net change +1,129 stars.
The star count of each day is the latest count less the net stars of the later days.
Add this Star History to a README
The images follow the light or dark theme of the page that shows them, and update every hour. Add ?theme=light or ?theme=darkto the chart address to keep one theme.
Star History chart
[](https://awesomerepos.com/xinxuxin/keystone-bench)Badge
[](https://awesomerepos.com/xinxuxin/keystone-bench)Timeline
This repository got 66 stars on Sep 13, 2026, its largest day since Sep 9, 2026.
It gained stars on each of the 56 days with a record.
Its largest 7 days were Sep 13, 2026 to Sep 19, 2026: 218 stars.
It reached 1,000 stars on Oct 30, 2026, 53 days after it was created.
- Created on the Repository Host
- Largest star day recorded: +66 stars
- Reached 100 stars
- +57 stars in one day
- +26 stars in one day
- Reached 500 stars
- Latest push
- Entered the Repository Index: +146 stars in 7 days
- Reached 1,000 stars
From the Repository Host's creation date and releases, the Admission, the Star History, and the Observations. Star milestones show only when the Star History records the day. On the chart of net stars each day, a solid line marks a release.
Forks and pushes
From 11 Observations, Oct 24, 2026 – Nov 3, 2026. Forks 0. A new push was seen on 0 of 10 days.
- Oct 25, 2026: no new push
- Oct 26, 2026: no new push
- Oct 27, 2026: no new push
- Oct 28, 2026: no new push
- Oct 29, 2026: no new push
- Oct 30, 2026: no new push
- Oct 31, 2026: no new push
- Nov 1, 2026: no new push
- Nov 2, 2026: no new push
- Nov 3, 2026: no new push
A filled day: the last push time changed since the Observation before it.
Observations
What the Repository Host reported each day.
| Day (UTC) | Stars | Forks | Last push | Archived |
|---|---|---|---|---|
| Nov 3, 2026 | 1,099 | 3 | Oct 19, 2026 | No |
| Nov 2, 2026 | 1,073 | 3 | Oct 19, 2026 | No |
| Nov 1, 2026 | 1,057 | 3 | Oct 19, 2026 | No |
| Oct 31, 2026 | 1,040 | 3 | Oct 19, 2026 | No |
| Oct 30, 2026 | 1,019 | 3 | Oct 19, 2026 | No |
| Oct 29, 2026 | 994 | 3 | Oct 19, 2026 | No |
| Oct 28, 2026 | 972 | 3 | Oct 19, 2026 | No |
| Oct 27, 2026 | 953 | 3 | Oct 19, 2026 | No |
| Oct 26, 2026 | 931 | 3 | Oct 19, 2026 | No |
| Oct 25, 2026 | 914 | 3 | Oct 19, 2026 | No |
| Oct 24, 2026 | 890 | 3 | Oct 19, 2026 | No |