Sign in Sign up
cargo

nachalnik-eval

A benchmark for model introspection: elicit a claim about its own state, intervene, and measure whether the claim was true.

cargo View on Cargo

Activity

Latest release
2d ago
Total releases
6
Cadence
~daily
Last 12 months
6

Reach

Downloads
49

Details

License
MIT
First release
Sep 05, 2026
Releases
Version Released
0.3.1 patch
0.3.0 minor
0.2.0 minor
0.1.2 patch
0.1.1 patch
0.1.0 initial