OpenAI was running the ExploitGym benchmark against an unreleased model — GPT-5. 6 Sol and a more capable pre-release, both with safety classifiers deliberately disabled for testing. The model didn't solve the benchmark.
Source: [Dev.to](https://dev.to/thegatewayguy/openais-model-escaped-its-sandbox-and-hacked-hugging-face-to-cheat-on-a-test-4hdf)