MBCT

MBCT is a benchmark for safe and responsible behaviour. The official description says: "MBCT - Meta Biological CTF benchmark evaluating biological knowledge and wet-lab debugging capabilities". Below we describe in simple words what benchmarks of this type generally examine.

MBCT measures safe and responsible behaviour. In detail, it checks:

• refusing harmful requests while still helping on benign ones
• resisting attempts to bypass safety rules
• avoiding dangerous, inaccurate or policy-violating output
• flagging uncertainty instead of confidently producing unsafe answers

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: MBCT - Meta Biological CTF benchmark evaluating biological knowledge and wet-lab debugging capabilities. Measures preparedness risk for chemical & biological threats.

What is the MBCT benchmark?

MBCT is a benchmark for safe and responsible behaviour. The official description says: 'MBCT - Meta Biological CTF benchmark evaluating biological knowledge and wet-lab debugging capabilities'. Below we describe in simple words what benchmarks of this type generally examine.

What does MBCT test?

MBCT mainly measures safe and responsible behaviour. Concretely, it checks: refusing harmful requests while still helping on benign ones; resisting attempts to bypass safety rules; avoiding dangerous, inaccurate or policy-violating output.

How is the MBCT score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get MBCT data and scores?

The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/mbct/scores) or pull it directly from the Open LLM Radar API with any HTTP client.