MafiaScope Benchmark

What is MafiaScope?

MafiaScope evaluates LLM agents in the social deduction game Mafia. It probes each agent's private beliefs after every public utterance, scoring them against…

Released

2026-07-12

Evaluates

General AI, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.10645

MafiaScope paper and code

• Paper https://arxiv.org/abs/2607.10645
• Code https://github.com/karpovilia/mafiascope
• Website https://karpovilia.github.io/mafiascope/

Which sources cite MafiaScope?

• MafiaScope

Related General AI, Language & Knowledge, cs.CL 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