List your company
ResearchFormerly WizWand

Discriminative Evaluation on CWQ (test)

92.88Binary AccuracyVicuna-1.5
45.955258.137670.3282.5024Feb 17, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Vicuna-1.5Size=33B, Prompting Strategy=Zero-shot CoT2024.0292.88
Vicuna-1.5Size=33B, Prompting Strategy=Zero-shot2024.0292.79
ChatGPTSize=175B, Prompting Strategy=Zero-shot CoT2024.0290.17
MistralSize=7B, Prompting Strategy=Zero-shot CoT2024.0289.88
ChatGPTSize=175B, Prompting Strategy=Zero-shot2024.0289.86
QwenSize=14B, Prompting Strategy=Zero-shot CoT2024.0288.86
QwenSize=14B, Prompting Strategy=Few-shot2024.0288.81
QwenSize=14B, Prompting Strategy=Zero-shot2024.0288.59
MistralSize=7B, Prompting Strategy=Zero-shot2024.0287.59
ChatGPTSize=175B, Prompting Strategy=Few-shot2024.0287.09
Vicuna-1.5Size=33B, Prompting Strategy=Few-shot2024.0284.91
LLaMA2-ChatSize=70B, Prompting Strategy=Zero-shot CoT2024.0280.71
ChatGPTSize=175B, Prompting Strategy=Few-shot CoT2024.0280.15
QwenSize=7B, Prompting Strategy=Few-shot2024.0279.64
LLaMA2-ChatSize=70B, Prompting Strategy=Zero-shot2024.0277.96
QwenSize=7B, Prompting Strategy=Zero-shot CoT2024.0276.13
QwenSize=14B, Prompting Strategy=Few-shot CoT2024.0275.87
QwenSize=7B, Prompting Strategy=Zero-shot2024.0274.76
QwenSize=7B, Prompting Strategy=Few-shot CoT2024.0273.23
MistralSize=7B, Prompting Strategy=Few-shot CoT2024.0269.98
Vicuna-1.5Size=33B, Prompting Strategy=Few-shot CoT2024.0267.05
LLaMA2-ChatSize=70B, Prompting Strategy=Few-shot2024.0256.99
MistralSize=7B, Prompting Strategy=Few-shot2024.0256.91
LLaMA2-ChatSize=70B, Prompting Strategy=Few-shot CoT2024.0247.76