Share your thoughts, 1 month free Claude Pro on usSee more

Mathematical Reasoning on TheoremQA

43.1Accuracy

Qwen2-72B

Updated 1mo ago

Evaluation Results

Method	Links
Qwen2-72B 2024.07		43.1
Mixtral-8x22B 2024.07		35.9
DeepSeekMath-7B-RL 2024.06		35.9
Qwen1.5-110B 2024.07		34.9
Qwen2-57B-A14B 2024.07		33.5
DART-Math-DSMath-7B 2024.06		32.5
Llama-3-70B 2024.07		32.3
DeepSeekMath-7B-DART-Math 2025.03		32.2
DART-Math-DSMath-7B 2024.06		32.2
Qwen1.5-72B 2024.07		29.3
Qwen1.5-32B 2024.07		28.8
DeepSeekMath-7B-Instruct 2025.03		28.1
DeepSeekMath-7B-DART-Math† 2025.03		27.4
DeepSeekMath-7B-RFT 2025.03		27.2
MathFusion-DSMath-7B 2025.03		27
MathFusion-DSMath-7B 2025.03		24.6
MathFusion-DSMath-7B 2025.03		23.8
DeepSeekMath-7B-MMIQC 2025.03		23.4
Mixtral-8x7B 2024.07		23.2
Llama3-8B-DART-Math† 2025.03		22.9
MathFusion-DSMath-7B 2025.03		22.8
MathFusion-Llama3-8B 2025.03		20
Llama3-8B-DART-Math 2025.03		19.4
MathFusion-DSMath-7B 2025.03		19
DeepSeekMath-7B-MetaMath 2025.03		18.9
MathFusion-Llama3-8B 2025.03		18.9
Mistral-7B-DART-Math† 2025.03		18.2
MathFusion-Mistral-7B 2025.03		18.1
Mistral-7B-DART-Math 2025.03		17
MathFusion-Llama3-8B 2025.03		17
Mistral-7B-WizardMath-V1.1 2025.03		16.6
Mistral-7B-RFT 2025.03		16.2
Mistral-7B-MMIQC 2025.03		16.2
Llama3-8B-MMIQC 2025.03		16.2
Llama3-8B-MetaMath† 2025.03		16.1
MathFusion-Mistral-7B 2025.03		15.5
MathFusion-Llama3-8B 2025.03		15.5
MathFusion-Mistral-7B 2025.03		15.2
Llama3-8B-RFT 2025.03		14.9
DeepSeekMath-7B-RefAug 2025.03		14.4
DeepSeekMath-7B-RefAug 2025.03		14
Mistral-7B-MetaMath 2025.03		14
Llama3-8B-MetaMath 2025.03		13.8
Llama3-8B-RefAug 2025.03		13.6
Llama3-8B-RefAug 2025.03		13
MathFusion-Mistral-7B 2025.03		12.8
Mistral-7B-MetaMath† 2025.03		12.2
Mistral-7B-RefAug 2025.03		11.1
DeepSeekMath-7B-Standard 2025.03		11
Mistral-7B-RefAug 2025.03		11
Llama3-8B-Standard 2025.03		10.9
Llama3-8B-MMIQC† 2025.03		10.6
Mistral-7B-Standard 2025.03		7.6
DeepSeekMath-7B-MMIQC† 2025.03		6.8
Mistral-7B-MMIQC† 2025.03		5.9