Arithmetic Reasoning on SingleOP
97.3AccuracyAutomatic Model Selection with LLMs
Evaluation Results
| Method | Links | |
|---|---|---|
| Automatic Model Selection with LLMsBackbone=GPT-4, Decoding strategy=Greedy2023.05 | 97.3 | |
| CoTBackbone=GPT-4, Decoding strategy=Greedy2023.05 | 97.2 | |
| Automatic Model Selection with LLMsBackbone=Codex, Decoding strategy=Greedy2023.05 | 96.3 | |
| PALBackbone=Codex, Decoding strategy=Greedy2023.05 | 95.4 | |
| PALBackbone=GPT-4, Decoding strategy=Greedy2023.05 | 95.2 | |
| CoTBackbone=ChatGPT, Decoding strategy=Greedy2023.05 | 94.8 | |
| Automatic Model Selection with LLMsBackbone=ChatGPT, Decoding strategy=Greedy2023.05 | 94.8 | |
| CoTBackbone=Codex, Decoding strategy=Greedy2023.05 | 92.7 | |
| PALBackbone=ChatGPT, Decoding strategy=Greedy2023.05 | 90.7 |