List your company

Mathematical Reasoning on MATH (test) (EM)

48.67Exact Match (EM)MetaTuner-J
15.847624.368832.8941.4112Sep 29, 2025

Evaluation results

MethodLinks
MetaTuner-JBackbone=Qwen2.5-7B, Method Category=Hybrid2025.0948.67
MetaTuner-IBackbone=Qwen2.5-7B, Method Category=Hybrid2025.0948.22
DPOBackbone=Qwen2.5-7B, Method Category=Fine-Tuning2025.0943.78
PPOBackbone=Qwen2.5-7B, Method Category=Fine-Tuning2025.0941.78
KTOBackbone=Qwen2.5-7B, Method Category=Fine-Tuning2025.0941.78
BetterTogetherBackbone=Qwen2.5-7B, Method Category=Hybrid2025.0941.56
SFTBackbone=Qwen2.5-7B, Method Category=Fine-Tuning2025.0941.33
MetaTuner-JBackbone=Qwen2.5-3B, Method Category=Hybrid2025.0941.33
MetaTuner-IBackbone=Qwen2.5-3B, Method Category=Hybrid2025.0940.89
DPOBackbone=Qwen2.5-3B, Method Category=Fine-Tuning2025.0936.59
BetterTogetherBackbone=Qwen2.5-3B, Method Category=Hybrid2025.0935.78
PPOBackbone=Qwen2.5-3B, Method Category=Fine-Tuning2025.0934.22
KTOBackbone=Qwen2.5-3B, Method Category=Fine-Tuning2025.0933.78
BPOBackbone=Qwen2.5-7B, Method Category=Prompt Optimization2025.0932.67
RLPromptBackbone=Qwen2.5-7B, Method Category=Prompt Optimization2025.0931.33
SFTBackbone=Qwen2.5-3B, Method Category=Fine-Tuning2025.0929.33
CFPOBackbone=Qwen2.5-7B, Method Category=Prompt Optimization2025.0927.11
BPOBackbone=Qwen2.5-3B, Method Category=Prompt Optimization2025.0926.44
RLPromptBackbone=Qwen2.5-3B, Method Category=Prompt Optimization2025.0922.67
OPROBackbone=Qwen2.5-7B, Method Category=Prompt Optimization2025.0922
OPROBackbone=Qwen2.5-3B, Method Category=Prompt Optimization2025.0921
Qwen2.5Backbone=Qwen2.5-7B, Method Category=Vanilla2025.0918.44
CFPOBackbone=Qwen2.5-3B, Method Category=Prompt Optimization2025.0917.78
Qwen2.5Backbone=Qwen2.5-3B, Method Category=Vanilla2025.0917.11