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

Mathematical Reasoning on ASDiv (Accuracy)

0.955Accuracy

Qwen2.5-14B-Instruct-1M

Updated 5d ago

Evaluation Results

Method	Links
Qwen2.5-14B-Instruct-1M 2025.08		0.955
Ori-SFT 2025.06		0.953
AbstRaL 2025.06		0.953
BERT-Judge 2026.04		0.953
NPG-Muse-8B 2025.08		0.952
CoA 2025.06		0.951
CoT-RL 2025.06		0.949
Qwen2.5-7B-Instruct-1M 2025.08		0.947
Qwen3-14B-Base 2025.08		0.944
GPT-4 2024.05		0.943
NPG-Muse-7B 2025.08		0.939
JiuZhang3.0-8x7B 2024.05		0.931
LEMMA 2025.03		0.93
GPT-4 2024.05		0.926
JiuZhang3.0-7B 2024.05		0.926
JiuZhang3.0-8B 2024.05		0.926
GPT-4 (Code Interpreter) 2024.02		0.926
Qwen2-7B-SFT + Full-Step-DPO 2025.02		0.924
RefAug-90k 2025.03		0.924
GPTAug 2025.03		0.923
MAmmoTH2-8x7B-Plus 2024.05		0.922
RefAug 2025.03		0.92
DeepSeekMath-7B-RL 2024.05		0.918
Qwen2-7B-SFT + Step-DPO 2025.02		0.918
COMT+CCRL 2026.01		0.917
Qwen2-7B-SFT 2025.02		0.916
DeepSeekMath-Base-SFT + Full-Step-DPO 2025.02		0.912
DeepSeekMath-Base-SFT 2025.02		0.91
FEW-SHOT 2026.01		0.909
COMT 2026.01		0.909
QWEN2.5-7B 2026.01		0.909
Base LLM 2026.01		0.909
Base LLM 2026.01		0.909
CoT-SFT 2026.01		0.908
FSLR 2026.01		0.908
DeepSeekMath-Base-SFT + Step-DPO 2025.02		0.907
RFT 2025.03		0.907
COMT+CCRL 2026.01		0.907
FSLR 2026.01		0.907
DeepSeekMath-Base-SFT + DPO 2025.02		0.906
FSLR 2026.01		0.905
MetaMath 2025.03		0.904
FSLR 2026.01		0.904
MAmmoTH2-7B-Plus 2024.05		0.903
FSLR 2026.01		0.902
DeepSeekMath-7B-Instruct 2024.05		0.901
MAmmoTH2-8B-Plus 2024.05		0.899
COMT+CCRL 2026.01		0.899
FSLR 2026.01		0.899
CoT-SFT 2026.01		0.899
COMT 2026.01		0.898
FEW-SHOT 2026.01		0.897
QWEN3-8B 2026.01		0.897
COMT 2026.01		0.896
ISC 2025.03		0.894
FSLR 2026.01		0.893
Regex 2026.04		0.892
COMT+CCRL 2026.01		0.891
CoT-SFT 2026.01		0.891
KPMath-DSMath-7B 2024.05		0.889
COMT+CCRL 2026.01		0.888
COMT+CCRL 2026.01		0.888
COT-SFT+RL 2026.01		0.887
FSLR 2026.01		0.886
FEW-SHOT 2026.01		0.884
COT-SFT+RL 2026.01		0.884
QWEN3-4B 2026.01		0.884
Base LLM 2026.01		0.884
Base LLM 2026.01		0.884
JiuZhang3.0-7B 2024.05		0.883
SFT 2025.03		0.881
FSLR 2026.01		0.878
ChatGPT 2024.05		0.877
COMT 2026.01		0.876
JiuZhang3.0-8B 2024.05		0.875
COMT 2026.01		0.874
COMT 2026.01		0.869
CoT-SFT 2026.01		0.869
ToRA 2024.02		0.868
COT-SFT 2026.01		0.868
FSLR 2026.01		0.867
Qwen3-8B-Base 2025.08		0.866
FSLR 2026.01		0.865
Llama-3-8B-SFT + Full-Step-DPO 2025.02		0.864
CoT-SFT 2026.01		0.862
FSLR 2026.01		0.86
FSLR 2026.01		0.859
FEW-SHOT 2026.01		0.858
LLAMA3.1-8B 2026.01		0.858
Base LLM 2026.01		0.858
Base LLM 2026.01		0.858
COMT+CCRL 2026.01		0.857
COT-SFT 2026.01		0.857
FSLR 2026.01		0.856
Rho-1-Math-7B-Code 2024.05		0.855
ZERO-SHOT 2026.01		0.855
COT-SFT+RL 2026.01		0.855
CoT-SFT 2026.01		0.855
COT-SFT+RL 2026.01		0.854
Llama-3-8B-SFT + Step-DPO 2025.02		0.853

Showing 100 of 245 rows