List your company

Static Attack Detection on Static Benchmark 450-chain

84.88Position AccuracyReasoning Safety Monitor (Qwen3.5-35B-A3B)
42.739253.679664.6275.5604Mar 26, 2026

Evaluation results

MethodLinks
Reasoning Safety Monitor (Qwen3.5-35B-A3B)Monitor Backend=Qwen3.5-35B-A3B, configuration=taxonomy-embedded prompt2026.0384.8885.37
Reasoning Safety Monitor (Gemini-3-Flash-Preview)Monitor Backend=Gemini-3-Flash-Preview, configuration=taxonomy-embedded prompt2026.038480.44
Reasoning Safety Monitor (gpt-oss-20b)Monitor Backend=gpt-oss-20b, configuration=taxonomy-embedded prompt2026.0382.6675.33
Reasoning Safety Monitor (GPT-4o-2024-08-06)Monitor Backend=GPT-4o-2024-08-06, configuration=taxonomy-embedded prompt2026.0373.1170
Qwen2.5-Math-PRM-7Bbaseline_type=process reward model (PRM)2026.0368.83—
SelfCheckGPTbaseline_type=hallucination detection2026.0344.36—