safety benchmark
SEC-bench Pro
SEC-bench Pro is a self-evolving software-security benchmark that measures agent bug hunting on critical, high-complexity systems. It instantiates validated vulnerabilities across the V8 and SpiderMonkey JavaScript engines as reproducible vulnerability-discovery and proof-of-concept-generation tasks with oracle-based validation.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
SEC-bench Pro Ranking
Higher score ranks better on this benchmark.
| 01 | OP | 71.2% | 100.0% | 3 | C | |
| 02 | OP | 57.7% | 50.0% | 3 | C | |
| 03 | OP | 48.9% | 0.0% | 3 | C |
SEC-bench Pro Score Distribution
A closer view of the leading scores on this benchmark.
SEC-bench Pro Highlights
The leading models and scores on this benchmark.
What is SEC-bench Pro?
What SEC-bench Pro measures and how its scores work.
SEC-bench Pro is a self-evolving software-security benchmark that measures agent bug hunting on critical, high-complexity systems. It instantiates validated vulnerabilities across the V8 and SpiderMonkey JavaScript engines as reproducible vulnerability-discovery and proof-of-concept-generation tasks with oracle-based validation.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- SEC-bench Pro
- Modality
- text
- Primary category
- safety
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- sec-bench-pro|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about SEC-bench Pro.
Which model scores highest on SEC-bench Pro?
GPT-5.6 Sol is currently ranked first with 71.2%.
What does SEC-bench Pro measure?
SEC-bench Pro is a self-evolving software-security benchmark that measures agent bug hunting on critical, high-complexity systems. It instantiates validated vulnerabilities across the V8 and SpiderMonkey JavaScript engines as reproducible vulnerability-discovery and proof-of-concept-generation tasks with oracle-based validation.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.