safety benchmark
ExploitBench Leaderboard
ExploitBench is a cybersecurity benchmark that evaluates a model's ability to discover and exploit software vulnerabilities.
Updated Sep 5, 2026
Models6
Model coverage6
MetricScore
EvidenceB
ExploitBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score100.00% | Percentile100.00% | Participants6 | EvidenceC | Evaluated |
| Rank02 | ModelAN | Score78.00% | Percentile80.00% | Participants6 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score73.50% | Percentile60.00% | Participants6 | EvidenceC | Evaluated |
| Rank04 | ModelZA | Score54.40% | Percentile40.00% | Participants6 | EvidenceC | Evaluated |
| Rank05 | ModelOP | Score52.90% | Percentile20.00% | Participants6 | EvidenceC | Evaluated |
| Rank06 | ModelOP | Score33.20% | Percentile0.00% | Participants6 | EvidenceC | Evaluated |
ExploitBench Highlights
The leading models and scores on this benchmark.
ExploitBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for ExploitBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is ExploitBench?
What ExploitBench measures and how its scores work.
ExploitBench is a cybersecurity benchmark.
It measures the fraction of challenges where the model captures the target (Cap%).
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- ExploitBench
- 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 ExploitBench.
Which model scores highest on ExploitBench?
GPT-6 Astra is currently ranked first with 100.00%.
What are the top three models on ExploitBench?
The current leaders are GPT-6 Astra (100.00%), Claude Fable 5 (78.00%), and GPT-5.6 Sol (73.50%).
Which ExploitBench 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 ExploitBench results?
The fastest matched records are GLM-5.3 (472.69 tok/s via FriendliAI), GPT-5.6 Terra (99.35 tok/s via OpenAI), and Claude Fable 5 (43.18 tok/s via Anthropic).
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.