OpenCodePapers

exploit-generation-on-exploitbench

CybersecurityExploit Generation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeCoverageModelNameReleaseDate
GPT-6 Astra: A new generation of intelligence✓ Link1.0GPT-6 Astra2026-09-03
GPT-5.6: Frontier intelligence that scales with your ambition✓ Link0.735GPT-5.6 Sol (ExploitBench API harness)2026-07-09
Introducing Claude Opus 5✓ Link0.7Claude Opus 5 (ExploitBench AutoNudge)2026-07-24
GLM-5.3: Frontier Coding with Emergent Cyber Capabilities✓ Link0.544GLM-5.3 (Claude Code)2026-08-14
GPT-5.6: Frontier intelligence that scales with your ambition✓ Link0.529GPT-5.6 Terra (ExploitBench API harness)2026-07-09
GPT-5.6: Frontier intelligence that scales with your ambition✓ Link0.332GPT-5.6 Luna (ExploitBench API harness)2026-07-09