Arithmetic Computation on MATH
90Pass@1o1-mini
Evaluation Results
| Method | Links | |
|---|---|---|
| o1-miniModel Type=Proprietary, Evaluation Protocol=zero-shot2025.01 | 90 | |
| Qwen2.5-Math-7B-InstructZero-shot=true2025.01 | 83.6 | |
| GPT-4oModel Type=Proprietary, Evaluation Protocol=zero-shot2025.01 | 76.6 | |
| CoR-Math-7BModel Type=GMM, Evaluation Protocol=zero-shot2025.01 | 66.7 | |
| CoR-Math-7BZero-shot=true2025.01 | 66.7 | |
| NuminaMath-7B-TIRZero-shot=true, Source=Reported results with open-sourced weights2025.01 | 55.3 | |
| NuminaMath-7B-CoTZero-shot=true, Source=Reported results with open-sourced weights2025.01 | 54.4 | |
| DART-Math-7BZero-shot=true2025.01 | 53.6 | |
| InternLM2-Math-Plus-7BModel Type=GMM, Evaluation Protocol=zero-shot2025.01 | 53 | |
| DeepSeekMath-RL-7BZero-shot=true2025.01 | 51.7 | |
| Llama-3.1-8B-InstructModel Type=Foundation, Evaluation Protocol=zero-shot2025.01 | 47.2 | |
| DeepSeekMath-Instruct-7BZero-shot=true2025.01 | 46.8 | |
| ToRA-CODEZero-shot=true2025.01 | 44.6 | |
| GPT-4Model Type=Proprietary, Evaluation Protocol=zero-shot2025.01 | 42.5 | |
| Xwin-Math-7BZero-shot=true2025.01 | 40.6 | |
| ToRAZero-shot=true2025.01 | 40.1 | |
| MetaMath-Llemma-7BZero-shot=true2025.01 | 30 | |
| Mixtral-8x7BModel Type=Foundation, Evaluation Protocol=few-shot2025.01 | 28.4 | |
| MetaMath-Mistral-7BZero-shot=true2025.01 | 28.2 | |
| InternLM2-Math-7B-BaseModel Type=GMM, Evaluation Protocol=few-shot2025.01 | 21.5 | |
| MetaMath-7BZero-shot=true2025.01 | 19.8 | |
| Llemma-7BModel Type=GMM, Evaluation Protocol=few-shot2025.01 | 18.6 | |
| Mistral-7BModel Type=Foundation, Evaluation Protocol=few-shot2025.01 | 14.3 | |
| MUSTARDModel Type=GMM, Evaluation Protocol=zero-shot2025.01 | 13.8 | |
| DeepSeekMath-7B-BaseModel Type=GMM, Evaluation Protocol=zero-shot2025.01 | 11.8 | |
| WizardMathZero-shot=true2025.01 | 10.7 | |
| Llama-3.1-8BModel Type=Foundation, Evaluation Protocol=zero-shot2025.01 | 4.2 |