Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
TamperBenchgithub.com · Low evidenceTamperBench is an open-source toolkit for benchmarking the tamper-resistance of open-weight large language models (LLMs). It supports red-teaming LLMs with tampering attacks such as fine-tuning, jailbreak-tuning, and embedding attacks. It provides evaluation tools for safety and utility, including StrongREJECT and MMLU-Pro, and is released under the MIT license.
The market map
AI Red Teaming Services →Where AI ranks TamperBench