Theorem Proving on TheoremQA
13.5AccuracyInternLM2-20B
Evaluation Results
| Method | Links | |
|---|---|---|
| InternLM2-20Bshots=0-shot, model_size_group=~20B2024.03 | 13.5 | |
| InternLM2-7Bshots=0-shot, model_size_group=~7B2024.03 | 10.5 | |
| Qwen-14Bshots=0-shot, model_size_group=~20B2024.03 | 10.4 | |
| ChatGLM3-6B-Baseshots=0-shot, model_size_group=~7B2024.03 | 6.5 | |
| Qwen-7Bshots=0-shot, model_size_group=~7B2024.03 | 5 | |
| Baichuan2-13B-Baseshots=0-shot, model_size_group=~20B2024.03 | 4.6 | |
| InternLM2-20B-Baseshots=0-shot, model_size_group=~20B2024.03 | 3.3 | |
| InternLM2-7B-Baseshots=0-shot, model_size_group=~7B2024.03 | 2.6 | |
| Llama2-13Bshots=0-shot, model_size_group=~20B2024.03 | 2.6 | |
| Mixtral-8x7B-v0.1shots=0-shot, model_size_group=~20B2024.03 | 2.5 | |
| Mistral-7B-v0.1shots=0-shot, model_size_group=~7B2024.03 | 1.8 | |
| Baichuan2-7B-Baseshots=0-shot, model_size_group=~7B2024.03 | 1.6 | |
| Llama2-7Bshots=0-shot, model_size_group=~7B2024.03 | 1 |