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…
- Modality
- text
- Categories
- safety, agents, code
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 3
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-5.6 Luna | OpenAI | 0.489 | 2026-07-09 | evidence |
| GPT-5.6 Sol | OpenAI | 0.712 | 2026-07-09 | evidence |
| GPT-5.6 Terra | OpenAI | 0.577 | 2026-07-09 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.