Skip to main content
BenchLM

SEC-Bench Pro

We show this table for reference; we do not rank on it.

Data verified 34 confirmed releases in the last 30 daysFollow model changes

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.

8 modelsAgenticCurrentDisplay onlyUpdated September 27, 2026

Benchmark score table (8 models)

Score
1
GPT-6 AstraOpenAI · Closed
85.4%
2
GPT-5.6 SolOpenAI · Closed
71.2%
3
GPT-6 SolOpenAI · Closed
66.3%
4
MiMo-V2.6-ProXiaomi · Open weight
66.3%
5
DeepSeek V4.1 FlashDeepSeek · Open weight
62.8%
6
MiMo-V2.6-FlashXiaomi · Open weight
47.5%
7
GPT-5.5OpenAI · Closed
45.8%
8
GPT-6 LunaOpenAI · Closed
34.2%

Among 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

CurrentDisplay only

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.

Last updated: September 27, 2026 · BenchLM version SEC-Bench Pro 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.