ExploitGym as reported in the DeepSeek September 10, 2026 release table. Time budget was not supplied; kept separate from 2h, 6h and unlimited protocols.
Browse the latest scores, model modes, release dates, and parameter sizes for ExploitGym (budget unspecified).
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
— |  GPT-5.6 Sol Thinking Level · MaxTools | 33.70 | 2026-06-26 | Unknown | Closed |
— |  DeepSeek-V4.1-Flash Thinking Level · MaxTools | 15.30 | 2026-09-10 | 552B | Unknown |
— |  GLM-5.3 Thinking Level · MaxTools | 15.00 | 2026-08-14 | 744B | Conditional |
— | DeepSeek-V4-Flash Thinking Level · MaxTools | 1.80 | 2026-04-24 | 284B | Free Commercial |
