Benchmark

ExploitGym

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities across userspace programs, Google's V8 engine, and the Linux…

Modality
text
Categories
safety, agents, code
Openness
unknown
Source
llm_stats
Reported scores
4

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
GLM-5.3Z.ai0.152026-08-14evidence
GPT-5.6 LunaOpenAI0.1242026-07-09evidence
GPT-5.6 SolOpenAI0.3372026-07-09evidence
GPT-5.6 TerraOpenAI0.2322026-07-09evidence

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.