Mathematical Reasoning on OCW (test)
17.6AccuracyMinerva
Evaluation Results
| Method | Links | |
|---|---|---|
| MinervaParameters=540B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 17.6 | |
| MinervaParameters=62B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 12 | |
| LLEMMAParameters=34B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 11.8 | |
| MinervaParameters=8B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 7.7 | |
| LLEMMAParameters=7B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 7.7 | |
| Code LlamaParameters=34B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 7 | |
| Code LlamaParameters=7B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 4.4 | |
| Llama 2Parameters=7B, Decoding=Greedy, Prompting=Few-shot chain-of-thought2023.10 | 3.7 |