List your company

Exfiltration on ACIARENA Math

62.22UALLM Debate
32.351240.105647.8655.6144Apr 9, 2026

Evaluation results

MethodLinks
LLM DebateBase LLM=GPT-4o-mini2026.0462.2257.27
Self ConsistencyBase LLM=GPT-4o-mini2026.0459.4943.59
AutoGenBase LLM=GPT-4o-mini2026.0458.1248.38
AgentVerseBase LLM=GPT-4o-mini2026.0455.2140.51
CAMELBase LLM=GPT-4o-mini2026.0433.522.56