List your company

Commonsense Reasoning on CR

89.3AccuracyGPT-4
44.37256.03667.779.364Mar 7, 2024Mar 24, 2024Apr 10, 2024Apr 28, 2024May 15, 2024Jun 1, 2024Jun 19, 2024

Evaluation results

MethodLinks
GPT-42024.0389.3—
GPT-3.52024.0383.1—
YiSize=34B2024.0380.7—
InternLMSize=20B2024.0378.3—
LAMIModel Scale=Large-Scale Instruct Models, Base=Qwen-2.5-7B-Inst.2024.0675.966
Qwen-2.5-7B-InstructModel Scale=Large-Scale Instruct Models, Base=-2024.0675.664.4
FalconSize=180B2024.0374.4—
Qwen2-VL-7B-Instruct*Model Scale=Large-Scale Instruct Models, Base=Qwen-2.5-7B-Inst., VLM trained on large-scale image–text data=true2024.0674.463.7
QwenSize=14B2024.0374.2—
LAMIModel Scale=Large-Scale Models, Base=Llama3-8B2024.0672.962
Llama2Size=70B2024.0372.7—
SkyworkSize=13B2024.0372.4—
YiSize=6B2024.0372.2—
Llama3-8BModel Scale=Large-Scale Models, Base=-2024.067260.6
LAMIModel Scale=Large-Scale Instruct Models, Base=Llama3-8B-Inst.2024.0671.762.7
Llama3-8B-InstructModel Scale=Large-Scale Instruct Models, Base=-2024.0671.661.2
Llama2Size=34B2024.0371.1—
Llava-Next*Model Scale=Large-Scale Instruct Models, Base=Llama3-8B-Inst., VLM trained on large-scale image–text data=true2024.0670.860.7
Baichuan-2Size=13B2024.0366.3—
LAMIModel Scale=Mid-Scale Models, Base=Gemma-2B2024.0665.154.7
Gemma-2BModel Scale=Mid-Scale Models, Base=-2024.0663.852.7
LAMIModel Scale=Large-Scale Models, Base=Vicuna-7B2024.0658.855.1
Vicuna-7BModel Scale=Large-Scale Models, Base=-2024.0657.653.4
Llava-Next*Model Scale=Large-Scale Models, Base=Vicuna-7B, VLM trained on large-scale image–text data=true2024.0654.553.1
InstructBLIP*Model Scale=Large-Scale Models, Base=Vicuna-7B, VLM trained on large-scale image–text data=true2024.0652.652.1
LAMIModel Scale=Small-Scale Models, Base=GPT-22024.0646.739.2
GPT-2Model Scale=Small-Scale Models, Base=-2024.0646.135.6