safety benchmark
SEC-bench Pro Leaderboard
SEC-bench Pro is a software-security benchmark for evaluating agent bug hunting on critical, high-complexity systems.
Updated Sep 5, 2026
Models4
Model coverage4
MetricScore
EvidenceB
SEC-bench Pro Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score85.40% | Percentile100.00% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelOP | Score71.20% | Percentile66.67% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score57.70% | Percentile33.33% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score48.90% | Percentile0.00% | Participants4 | EvidenceC | Evaluated |
SEC-bench Pro Highlights
The leading models and scores on this benchmark.
SEC-bench Pro Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for SEC-bench Pro
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is SEC-bench Pro?
What SEC-bench Pro measures and how its scores work.
SEC-bench Pro instantiates validated vulnerabilities across the V8 and SpiderMonkey JavaScript engines as reproducible vulnerability-discovery and proof-of-concept-generation tasks with oracle-based validation.
It measures agent bug hunting through vulnerability discovery and proof-of-concept generation, reported as a Score ratio.
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
- No
- Evaluation key
- overall
LLM Stats. 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-6 Astra is currently ranked first with 85.40%.
What are the top three models on SEC-bench Pro?
The current leaders are GPT-6 Astra (85.40%), GPT-5.6 Sol (71.20%), and GPT-5.6 Terra (57.70%).
Which SEC-bench Pro model has the lowest official input price?
GPT-5.6 Luna has the lowest matched official input price at $0.20 input / $1.2 output per 1M tokens.
Which models are fastest among SEC-bench Pro results?
The fastest matched records are GPT-5.6 Terra (99.35 tok/s via OpenAI), GPT-5.6 Luna (41.87 tok/s via OpenAI), and GPT-6 Astra (30.66 tok/s via OpenAI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.