8-Puzzle Solving on 8-Puzzle multi-solution
76.33Multi AccuracyXoT (w/ 1 r)
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| XoT (w/ 1 r)LLM=GPT-42023.11 | 76.33 | 1.52 | 4.3 | 66.66 | |
| XoT (w/ 1 r)LLM=GPT-3.52023.11 | 27.45 | 2.85 | 4.19 | 52.06 | |
| GoT (k=3)LLM=GPT-42023.11 | 16.61 | 2.7 | 22.76 | — | |
| CoTLLM=GPT-42023.11 | 7.84 | 1.21 | 1 | — | |
| CoT-SCLLM=GPT-42023.11 | 6.58 | 2.08 | 10 | — | |
| ToT (b=3)LLM=GPT-42023.11 | 5.6 | 2.97 | 54.13 | — | |
| GoT (k=3)LLM=GPT-3.52023.11 | 3.36 | 2.96 | 24.18 | — | |
| ToT (b=3)LLM=GPT-3.52023.11 | 2.52 | 2.98 | 55.86 | — | |
| CoT-SCLLM=GPT-3.52023.11 | 1.54 | 1.9 | 10 | — | |
| CoTLLM=GPT-3.52023.11 | 1.43 | 2.05 | 1 | — | |
| IOLLM=GPT-42023.11 | 0.84 | 2.97 | 1 | — | |
| IOLLM=GPT-3.52023.11 | 0 | 2.47 | 1 | — |