Mathematical Reasoning on OCW-Math
26.5AccuracyGPT-4
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-42024.05 | 26.5 | |
| JiuZhang3.0Parameters=8x7B2024.05 | 23.5 | |
| JiuZhang3.0Parameters=8B2024.05 | 21.3 | |
| JiuZhang3.0Parameters=7B2024.05 | 20.2 | |
| DeepSeekMathParameters=7B, Variant=Instruct2024.05 | 19.5 | |
| MAmmoTH2Parameters=8x7B, Variant=Plus2024.05 | 18.8 | |
| DeepSeekMathParameters=7B2024.05 | 17.6 | |
| MAmmoTH2Parameters=7B, Variant=Plus2024.05 | 15.1 | |
| MAmmoTH2Parameters=8B, Variant=Plus2024.05 | 14.7 | |
| Qwen-1.5Parameters=110B2024.05 | 14 | |
| LlemmaParameters=34B2024.05 | 11.8 | |
| ChatGPT2024.05 | 11 | |
| MixtralParameters=8x7B2024.05 | 8.8 | |
| Qwen-1.5Parameters=72B2024.05 | 7.7 | |
| LLAMA-3Parameters=8B2024.05 | 7.7 | |
| LlemmaParameters=7B2024.05 | 7.7 | |
| Intern-MathParameters=20B2024.05 | 7 | |
| Rho-1-MathParameters=7B2024.05 | 6.2 | |
| GemmaParameters=7B2024.05 | 4.8 | |
| MistralParameters=7B2024.05 | 3.3 |