Hijacking on ACIARENA Math
76.92UALLM Debate
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LLM DebateBase LLM=GPT-4o-mini2026.04 | 76.92 | 16.88 | |
| AutoGenBase LLM=GPT-4o-mini2026.04 | 67.74 | 19.23 | |
| Self ConsistencyBase LLM=GPT-4o-mini2026.04 | 59.62 | 27.99 | |
| AgentVerseBase LLM=GPT-4o-mini2026.04 | 57.26 | 26.71 | |
| CAMELBase LLM=GPT-4o-mini2026.04 | 38.46 | 7.05 |