Proof, not preference.
Muence runs a real exploit against the code and the app's own tests. A model scores only when the attack dies — and nothing else breaks.
$ muence verify patch
Evaluating auth/session-fix.ts
Reward earned
all executable gates passed
1,000
execution-verified tasks
4 gates
before a task can score
0 / 1
a program is the final judge
Why it matters
Code can work and still be dangerously wrong.
Training rewards functional output: does the app run? Security is usually absent from that loop. Models learn to ship a feature, even when the feature leaves an exploit behind.
Muence turns the missing signal into a runnable environment. The exploit must fail, and the original spec must still pass.
Inspect the benchmarkWhere models fail
Failure rate across verified security tasks
The executable loop
A reward signal that has to survive contact with reality.
Every environment starts with a working but vulnerable app, then proves both the bug and the fix using isolated, executable gates.
Generate
Start with realistic product code: logins, uploads, payments, and APIs — written without security guidance.
Prove
A runnable exploit proves the vulnerability exists. A held-out suite defines the app behavior that cannot break.
Reward
The patch earns a score only when the exploit fails and the product still works. That outcome trains the model.
Built for measurement and training
One engine, two ways to use it.
Evaluate the frontier today, then use the same executable tasks as the training environments that move the score.
Execution-Verified Benchmark
A public security benchmark built from tasks with real exploits, held-out specs, and hard pass/fail results.
- Boot · exploit · patch · re-verify
- Open VibeSec dataset and live model rankings
- Scores based on programs exiting 0 or 1
RL Environments
The same tasks become sandboxed reset / step / reward loops, ready to generate trajectories for post-training.
- Isolated execution with egress blocked
- A functional grader blocks reward hacking
- Rollouts export into post-training pipelines
Build with us
Make the reward worth optimizing.
Talk with us about the benchmark, data partnerships, or running your model through execution-verified environments.