Mathematical Reasoning on ConceptMath Middle-EN
90.12AccuracyGPT-3.5
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-3.5Prompt Setting=ZS-COT, Model Size=Proprietary2024.02 | 90.12 | |
| GPT-4Prompt Setting=ZS-COT, Model Size=Proprietary2024.02 | 89.83 | |
| GPT-4Prompt Setting=FS, Model Size=Proprietary2024.02 | 88.68 | |
| GPT-4Prompt Setting=ZS, Model Size=Proprietary2024.02 | 84.26 | |
| GPT-3.5Prompt Setting=ZS, Model Size=Proprietary2024.02 | 83.88 | |
| GPT-3.5Prompt Setting=FS, Model Size=Proprietary2024.02 | 82.73 | |
| Yi-34BPrompt Setting=ZS-COT, Model Size=34B2024.02 | 74.66 | |
| Qwen-72BPrompt Setting=ZS, Model Size=72B2024.02 | 74.66 | |
| Qwen-72BPrompt Setting=FS, Model Size=72B2024.02 | 73.99 | |
| Yi-34BPrompt Setting=ZS, Model Size=34B2024.02 | 72.26 | |
| InternLM2-Math-20BPrompt Setting=ZS-COT, Model Size=20B2024.02 | 71.21 | |
| InternLM2-Math-20BPrompt Setting=FS, Model Size=20B2024.02 | 70.83 | |
| DeepSeekMath-7BPrompt Setting=ZS-COT, Model Size=7B2024.02 | 69.87 | |
| Qwen-72BPrompt Setting=ZS-COT, Model Size=72B2024.02 | 69.87 | |
| Baichuan2-13BPrompt Setting=ZS-COT, Model Size=13B2024.02 | 69.67 | |
| Qwen-14BPrompt Setting=FS, Model Size=14B2024.02 | 67.85 | |
| Baichuan2-13BPrompt Setting=ZS, Model Size=13B2024.02 | 67.66 | |
| InternLM2-20BPrompt Setting=ZS-COT, Model Size=20B2024.02 | 67.47 | |
| DeepSeekMath-7BPrompt Setting=FS, Model Size=7B2024.02 | 66.31 | |
| InternLM2-7BPrompt Setting=ZS-COT, Model Size=7B2024.02 | 65.83 | |
| Yi-34BPrompt Setting=FS, Model Size=34B2024.02 | 65.83 | |
| Yi-6BPrompt Setting=ZS, Model Size=6B2024.02 | 65.55 | |
| Yi-6BPrompt Setting=ZS-COT, Model Size=6B2024.02 | 64.59 | |
| InternLM2-Math-20BPrompt Setting=ZS, Model Size=20B2024.02 | 64.11 | |
| InternLM2-Math-7BPrompt Setting=ZS, Model Size=7B2024.02 | 63.44 | |
| InternLM2-Math-7BPrompt Setting=FS, Model Size=7B2024.02 | 63.05 | |
| InternLM2-Math-7BPrompt Setting=ZS-COT, Model Size=7B2024.02 | 62.96 | |
| LLaMA2-70BPrompt Setting=ZS-COT, Model Size=70B2024.02 | 60.94 | |
| ChatGLM3-6BPrompt Setting=ZS-COT, Model Size=6B2024.02 | 60.17 | |
| Qwen-14BPrompt Setting=ZS-COT, Model Size=14B2024.02 | 59.6 | |
| LLaMA2-70BPrompt Setting=ZS, Model Size=70B2024.02 | 58.06 | |
| InternLM2-20BPrompt Setting=FS, Model Size=20B2024.02 | 56.72 | |
| DeepSeekMath-7BPrompt Setting=ZS, Model Size=7B2024.02 | 56.53 | |
| Yi-6BPrompt Setting=FS, Model Size=6B2024.02 | 56.05 | |
| InternLM2-7BPrompt Setting=FS, Model Size=7B2024.02 | 55.47 | |
| MAmmoTH-13BPrompt Setting=ZS, Model Size=13B2024.02 | 53.93 | |
| ChatGLM3-6BPrompt Setting=FS, Model Size=6B2024.02 | 51.34 | |
| ChatGLM3-6BPrompt Setting=ZS, Model Size=6B2024.02 | 51.25 | |
| MAmmoTH-13BPrompt Setting=FS, Model Size=13B2024.02 | 48.08 | |
| MetaMath-13BPrompt Setting=FS, Model Size=13B2024.02 | 47.5 | |
| LLaMA2-13BPrompt Setting=ZS-COT, Model Size=13B2024.02 | 46.45 | |
| MAmmoTH-13BPrompt Setting=ZS-COT, Model Size=13B2024.02 | 45.2 | |
| WizardMath-13BPrompt Setting=FS, Model Size=13B2024.02 | 45.11 | |
| InternLM2-20BPrompt Setting=ZS, Model Size=20B2024.02 | 45.11 | |
| LLaMA2-13BPrompt Setting=ZS, Model Size=13B2024.02 | 44.72 | |
| MetaMath-13BPrompt Setting=ZS, Model Size=13B2024.02 | 44.24 | |
| MetaMath-13BPrompt Setting=ZS-COT, Model Size=13B2024.02 | 43.47 | |
| LLaMA2-13BPrompt Setting=FS, Model Size=13B2024.02 | 43.09 | |
| Baichuan2-13BPrompt Setting=FS, Model Size=13B2024.02 | 40.4 | |
| LLaMA2-7BPrompt Setting=ZS-COT, Model Size=7B2024.02 | 39.16 | |
| Qwen-14BPrompt Setting=ZS, Model Size=14B2024.02 | 38.48 | |
| WizardMath-13BPrompt Setting=ZS-COT, Model Size=13B2024.02 | 37.72 | |
| InternLM2-7BPrompt Setting=ZS, Model Size=7B2024.02 | 37.04 | |
| WizardMath-13BPrompt Setting=ZS, Model Size=13B2024.02 | 36.85 | |
| LLaMA2-7BPrompt Setting=ZS, Model Size=7B2024.02 | 34.26 | |
| LLaMA2-7BPrompt Setting=FS, Model Size=7B2024.02 | 33.69 | |
| LLaMA2-70BPrompt Setting=FS, Model Size=70B2024.02 | 31.67 |