Murder Mystery Reasoning on MUSR murder (test)
75AccuracyInduced
Evaluation Results
| Method | Links | |
|---|---|---|
| InducedLLM Backbone=DeepSeek-V32026.06 | 75 | |
| Induced2026.06 | 75 | |
| Hand-designedLLM Backbone=DeepSeek-V32026.06 | 69 | |
| Hand2026.06 | 69 | |
| Program-of-ThoughtsLLM Backbone=DeepSeek-V32026.06 | 67 | |
| Program-of-Thoughts2026.06 | 67 | |
| Chain-of-ThoughtLLM Backbone=DeepSeek-V32026.06 | 60 | |
| CoT2026.06 | 60 | |
| Agent Workflow MemoryLLM Backbone=DeepSeek-V32026.06 | 47 | |
| AWM2026.06 | 47 | |
| ReActLLM Backbone=DeepSeek-V32026.06 | 45 | |
| ReAct2026.06 | 45 |