DEMM-Bench

What is DEMM-Bench?

A cross-regime benchmark for testing whether agent-runtime records are sufficient to reconstruct decision-level governance properties under deterministic…

Released

2026-05-30

Evaluates

Agents, General AI, Language & Knowledge

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.20634

DEMM-Bench paper, code and dataset

• Paper https://arxiv.org/abs/2606.20634
• Code https://github.com/agent-runtime-evidence/decision-evidence-benchmark
• Dataset https://huggingface.co/datasets/dev404ai/DEMM-Bench

Which sources cite DEMM-Bench?

• DEMM-Bench

Related Agents, General AI, Language & Knowledge benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench