Mathematical Reasoning on SAT (test)
71.9AccuracyLLEMMA
Evaluation Results
| Method | Links | |
|---|---|---|
| LLEMMAParameters=34B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 71.9 | |
| LLEMMAParameters=7B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 53.1 | |
| Code LlamaParameters=34B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 40.6 | |
| Llama 2Parameters=7B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 25 | |
| Code LlamaParameters=7B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 9.4 |