SEC-Bench Pro
We show this table for reference; we do not rank on it.
Cybersecurity benchmark for agentic vulnerability analysis and exploit-oriented security tasks.
Benchmark score on SEC-Bench Pro — September 27, 2026
We compile the SEC-Bench Pro rows from provider self-reports. GPT-6 Astra leads the table at 85.4%, followed by GPT-5.6 Sol (71.2%) and GPT-6 Sol (66.3%). We do not use these results to rank models overall.
GPT-6 Astra
OpenAI
GPT-5.6 Sol
OpenAI
GPT-6 Sol
OpenAI
8 modelsAgenticCurrentDisplay onlyUpdated September 27, 2026
Benchmark score table (8 models)
ScoreAmong the reported SEC-Bench Pro rows, GPT-6 Astra is first at 85.4%. The third row is 19.1 points behind. The broader top-10 range is 51.2 points, so the table still separates the published systems.
8 models have been evaluated on SEC-Bench Pro. The benchmark falls in the Agentic category. We keep these results separate from the weighted global scoring system, so they remain source-specific evidence. SEC-Bench Pro is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About SEC-Bench Pro
Year
2026
Tasks
Security engineering tasks
Format
Success rate
Difficulty
Advanced cybersecurity
OpenAI reports exact model results on SEC-Bench Pro in its GPT-5.6 launch table. BenchLM stores the provider-run values as display-only cyber evidence until benchmark-native results are available.
Freshness and provenance
Version
SEC-Bench Pro 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does SEC-Bench Pro measure?
Cybersecurity benchmark for agentic vulnerability analysis and exploit-oriented security tasks.
Which model scores highest on SEC-Bench Pro?
GPT-6 Astra by OpenAI currently leads with a score of 85.4% on SEC-Bench Pro.
How many models are evaluated on SEC-Bench Pro?
8 AI models have been evaluated on SEC-Bench Pro on BenchLM.
Compare top models on SEC-Bench Pro
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.