Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Problem Solving on Gaokao MathCloze
Loading...
72.9
Accuracy
Qwen2-Math-72B
2.388
20.694
39
57.306
Feb 5, 2024
Mar 13, 2024
Apr 20, 2024
May 28, 2024
Jul 4, 2024
Aug 11, 2024
Sep 18, 2024
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2-Math-72B
shot=5-shot, prompting...
2024.09
72.9
Qwen2.5-Math-72B
shot=5-shot, prompting...
2024.09
72.9
Qwen2.5-Math-7B
shot=5-shot, prompting...
2024.09
57.6
Qwen2-72B
shot=5-shot, prompting...
2024.09
55.9
Qwen2-Math-7B
shot=5-shot, prompting...
2024.09
48.3
Qwen2.5-Math-1.5B
shot=5-shot, prompting...
2024.09
47.5
Qwen2-7B
shot=5-shot, prompting...
2024.09
37.3
Qwen2-Math-1.5B
shot=5-shot, prompting...
2024.09
37.3
DeepSeek-Coder-V2-Lite-Base
shot=5-shot, prompting...
2024.09
25.4
DeepSeekMath-Base
Size=7B, Evaluation=Ch...
2024.02
20.3
DeepSeekMath-Base-7B
shot=5-shot, prompting...
2024.09
20.3
InternLM2-Math-Base-20B
shot=5-shot, prompting...
2024.09
16.9
Qwen2-1.5B
shot=5-shot, prompting...
2024.09
12.7
Llemma
Size=7B, Evaluation=Ch...
2024.02
11.9
Llemma
Size=34B, Evaluation=C...
2024.02
11.9
Llama-3.1-70B
shot=5-shot, prompting...
2024.09
11.9
Llama-3.1-8B
shot=5-shot, prompting...
2024.09
8.5
Mistral
Size=7B, Evaluation=Ch...
2024.02
5.1
Feedback
Search any
task
Search any
task