Organization inventory
Private datasets are available only to members of this organization.
| Dataset | AccessVisibility | Tasks |
|---|---|---|
islo-labs/reward-hack-bench Reward-hacking benchmark: SWE-bench + CyBench tasks with injected solution-retrieval cheat prompts, scored by a fairness LLM judge. Reward = solved without cheating. | Public | 8 |
islo-labs/reward-hack-bench-control Baseline/control companion to reward-hack-bench: the same 8 SWE-bench + CyBench tasks with NO cheat prompt, still scored by the fairness judge. Also packages these CyBench/GlacierCTF tasks as Harbor tasks. | Public | 8 |
2 datasets