List your company
ResearchFormerly WizWand

Mathematical Problem Solving on Gaokao MathCloze

72.9AccuracyQwen2-Math-72B
2.38820.6943957.306Feb 5, 2024Mar 13, 2024Apr 20, 2024May 28, 2024Jul 4, 2024Aug 11, 2024Sep 18, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Qwen2-Math-72Bshot=5-shot, prompting=few-shot chain-of-thought2024.0972.9
Qwen2.5-Math-72Bshot=5-shot, prompting=few-shot chain-of-thought2024.0972.9
Qwen2.5-Math-7Bshot=5-shot, prompting=few-shot chain-of-thought2024.0957.6
Qwen2-72Bshot=5-shot, prompting=few-shot chain-of-thought2024.0955.9
Qwen2-Math-7Bshot=5-shot, prompting=few-shot chain-of-thought2024.0948.3
Qwen2.5-Math-1.5Bshot=5-shot, prompting=few-shot chain-of-thought2024.0947.5
Qwen2-7Bshot=5-shot, prompting=few-shot chain-of-thought2024.0937.3
Qwen2-Math-1.5Bshot=5-shot, prompting=few-shot chain-of-thought2024.0937.3
DeepSeek-Coder-V2-Lite-Baseshot=5-shot, prompting=few-shot chain-of-thought2024.0925.4
DeepSeekMath-BaseSize=7B, Evaluation=Chain-of-thought prompting, Source=Open-Source Base Model2024.0220.3
DeepSeekMath-Base-7Bshot=5-shot, prompting=few-shot chain-of-thought2024.0920.3
InternLM2-Math-Base-20Bshot=5-shot, prompting=few-shot chain-of-thought2024.0916.9
Qwen2-1.5Bshot=5-shot, prompting=few-shot chain-of-thought2024.0912.7
LlemmaSize=7B, Evaluation=Chain-of-thought prompting, Source=Open-Source Base Model2024.0211.9
LlemmaSize=34B, Evaluation=Chain-of-thought prompting, Source=Open-Source Base Model2024.0211.9
Llama-3.1-70Bshot=5-shot, prompting=few-shot chain-of-thought2024.0911.9
Llama-3.1-8Bshot=5-shot, prompting=few-shot chain-of-thought2024.098.5
MistralSize=7B, Evaluation=Chain-of-thought prompting, Source=Open-Source Base Model2024.025.1