SOTA Mathematical Reasoning on CollegeMath (test) and PapersWithCode

48.3Accuracy

TATA

Updated 4d ago

Evaluation Results

Method	Links
TATA 2025.02		48.3
hybrid 2025.02		47.1
ensemble 2025.02		46.7
TATA 2025.02		46.4
ensemble 2025.02		46.1
hybrid 2025.02		45.8
GPT-Select 2025.02		44.4
hybrid 2025.02		44.2
GPT-Select 2025.02		44.1
ensemble 2025.02		44.1
TATA 2025.02		43.9
TATA 2025.02		43.4
hybrid 2025.02		43.1
ensemble 2025.02		43
ensemble 2025.02		42.9
GPT-Select 2025.02		42.7
DeepSeekMath-7B-VRT 2024.06		41.9
GPT-Select 2025.02		41.8
hybrid 2025.02		41.6
TATA 2025.02		41.6
DART-Math-DSMath-7B (Prop2Diff) 2024.06		40.7
DART-Math-DSMath-7B (Uniform) 2024.06		40.1
GPT-Select 2025.02		38.9
DART-Math-Llama3-70B (Uniform) 2024.06		38.5
DART-Math-Llama3-70B (Prop2Diff) 2024.06		37.9
Llama3-70B-MMIQC 2024.06		37.6
DeepSeekMath-7B-Instruct 2024.06		37.1
TATA 2025.02		37
Llama3-70B-VRT 2024.06		36.8
hybrid 2025.02		36.8
ensemble 2025.02		36.6
DeepSeekMath-7B-MMIQC 2024.06		35.3
GPT-Select 2025.02		35
DeepSeekMath-7B-ICL 2024.06		34.7
TATA 2025.02		34.2
Llama3-70B-ICL 2024.06		33.5
Llama2-70B-Xwin-Math-V1.1+ 2024.06		33.1
Llama3-70B-MetaMath 2024.06		31.9
hybrid 2025.02		30.8
GPT-Select 2025.02		30.6
ensemble 2025.02		29.6
Llama3-8B-MMIQC 2024.06		29.5
DART-Math-Mistral-7B (Prop2Diff) 2024.06		29.4
DART-Math-Llama3-8B (Prop2Diff) 2024.06		28.8
Mistral-7B-MMIQC 2024.06		28.5
Llama2-7B-Xwin-Math-V1.1+ 2024.06		27.6
hybrid 2025.02		27.5
DART-Math-Llama3-8B (Uniform) 2024.06		27.1
DART-Math-Mistral-7B (Uniform) 2024.06		26.9
TATA 2025.02		26.9
ensemble 2025.02		25.6
GPT-4 (0314) 2024.06		24.4
GPT-Select 2025.02		24.4
Mistral-7B-VRT 2024.06		24.2
Llama3-8B-VRT 2024.06		23.9
Mistral-7B-WizardMath-V1.1 (RL) 2024.06		23.1
Mistral-7B-MathScale 2024.06		21.8
Llama3-8B-MetaMath 2024.06		20.6
Llama3-8B-ICL 2024.06		19.9
Mistral-7B-MetaMath 2024.06		19.3
Mistral-7B-ICL 2024.06		17.9