Benchmark
ExploitGym Benchmark
What is ExploitGym?
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities across userspace programs, Google's V8 engine, and the Linux kernel…
- Modality
- text
- Evaluates
- safety, agents, code
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 4
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/exploitgym?top_n=500
ExploitGym results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GLM-5.3 | Z.ai | 0.15 | 2026-08-14 | evidence |
| GPT-5.6 Luna | OpenAI | 0.124 | 2026-07-09 | evidence |
| GPT-5.6 Sol | OpenAI | 0.337 | 2026-07-09 | evidence |
| GPT-5.6 Terra | OpenAI | 0.232 | 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.