SoCRATES Benchmark

What is SoCRATES?

SoCRATES is a benchmark for evaluating proactive LLM mediators in realistic, multi-domain testbeds. It contains 600 conflict scenarios across eight domains…

Released

2026-06-04

Evaluates

General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.05563

SoCRATES paper and code

• Paper https://arxiv.org/abs/2606.05563
• Code https://github.com/DISL-Lab/SoCRATES

Which sources cite SoCRATES?

• SoCRATES

Related General AI, Language & Knowledge, cs.AI 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