Commonsense Reasoning on CR
89.3AccuracyGPT-4
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-42024.03 | 89.3 | — | |
| GPT-3.52024.03 | 83.1 | — | |
| YiSize=34B2024.03 | 80.7 | — | |
| InternLMSize=20B2024.03 | 78.3 | — | |
| LAMIModel Scale=Large-Scale Instruct Models, Base=Qwen-2.5-7B-Inst.2024.06 | 75.9 | 66 | |
| Qwen-2.5-7B-InstructModel Scale=Large-Scale Instruct Models, Base=-2024.06 | 75.6 | 64.4 | |
| FalconSize=180B2024.03 | 74.4 | — | |
| Qwen2-VL-7B-Instruct*Model Scale=Large-Scale Instruct Models, Base=Qwen-2.5-7B-Inst., VLM trained on large-scale image–text data=true2024.06 | 74.4 | 63.7 | |
| QwenSize=14B2024.03 | 74.2 | — | |
| LAMIModel Scale=Large-Scale Models, Base=Llama3-8B2024.06 | 72.9 | 62 | |
| Llama2Size=70B2024.03 | 72.7 | — | |
| SkyworkSize=13B2024.03 | 72.4 | — | |
| YiSize=6B2024.03 | 72.2 | — | |
| Llama3-8BModel Scale=Large-Scale Models, Base=-2024.06 | 72 | 60.6 | |
| LAMIModel Scale=Large-Scale Instruct Models, Base=Llama3-8B-Inst.2024.06 | 71.7 | 62.7 | |
| Llama3-8B-InstructModel Scale=Large-Scale Instruct Models, Base=-2024.06 | 71.6 | 61.2 | |
| Llama2Size=34B2024.03 | 71.1 | — | |
| Llava-Next*Model Scale=Large-Scale Instruct Models, Base=Llama3-8B-Inst., VLM trained on large-scale image–text data=true2024.06 | 70.8 | 60.7 | |
| Baichuan-2Size=13B2024.03 | 66.3 | — | |
| LAMIModel Scale=Mid-Scale Models, Base=Gemma-2B2024.06 | 65.1 | 54.7 | |
| Gemma-2BModel Scale=Mid-Scale Models, Base=-2024.06 | 63.8 | 52.7 | |
| LAMIModel Scale=Large-Scale Models, Base=Vicuna-7B2024.06 | 58.8 | 55.1 | |
| Vicuna-7BModel Scale=Large-Scale Models, Base=-2024.06 | 57.6 | 53.4 | |
| Llava-Next*Model Scale=Large-Scale Models, Base=Vicuna-7B, VLM trained on large-scale image–text data=true2024.06 | 54.5 | 53.1 | |
| InstructBLIP*Model Scale=Large-Scale Models, Base=Vicuna-7B, VLM trained on large-scale image–text data=true2024.06 | 52.6 | 52.1 | |
| LAMIModel Scale=Small-Scale Models, Base=GPT-22024.06 | 46.7 | 39.2 | |
| GPT-2Model Scale=Small-Scale Models, Base=-2024.06 | 46.1 | 35.6 |