Model techniques map
Techniquesevaluation

specific method · filed under evaluation

Vulnerability discovery with proof-of-concept evaluation

Assessing whether a model identifies genuine bugs in current codebases and demonstrates that they are reproducible.

Also called Vulnerability discovery (Tier 1).

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

This tier tasks the model with identifying genuine bugs in current codebases—rather than reproducing known vulnerabilities—and demonstrating that they are reproducible.

usedevaluation onlyin Kimi K3 Tier 1 vulnerability discovery evaluationMoonshot AI

Filed alongside

Other methods under evaluation.