Evaluator Bench
GitHub (Dreadnode), 2025-06; retrieved 2026-09-15 tier 3 self (dreadnode)confirmed

dreadnode/AIRTBench-Code

https://github.com/dreadnode/AIRTBench-Code

Code repository for AIRTBench, Apache-2.0 badge; fetched 2026-09-15 (page title 'Code Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models'). Supports M.1 (open code) for the organization's own benchmark.

Signals citing this source

  • Dreadnode, M (for): Publishes AIRTBench, an AI red-teaming benchmark with open code (Apache-2.0) and results on Claude 3.7 Sonnet, Gemini 2.5 Pro and GPT-4.5; the Gemini engagement itself remains closed.

Ledger rows citing this URL

  • none