List your company
ResearchFormerly WizWand

Mathematical Reasoning on MATH (Acc., Time)

94.2AccuracyNTele-R1-32B
28.05645.22862.479.572Aug 13, 2025Sep 28, 2025Nov 14, 2025Dec 31, 2025Feb 16, 2026Apr 4, 2026May 21, 2026
Updated 4mo ago

Evaluation results

MethodLinks
NTele-R1-32B2025.0894.2—
DS-32B2025.0888.28—
GraphFlowModel=Qwen-2.5-7B2026.0576.415.22
AFlowModel=Qwen-2.5-7B2026.0572.116.6
LLMCompilerModel=Qwen-2.5-7B2026.0568.814.67
AgentKBModel=Qwen-2.5-7B2026.0568.315.85
AutoFlowModel=Qwen-2.5-7B2026.0568.217.95
MetaGPTModel=Qwen-2.5-7B2026.0566.614.52
TaskWeaverModel=Qwen-2.5-7B2026.0565.518.26
VanillaModel=Qwen-2.5-7B2026.0560.49.63
GraphFlowModel=Llama-3.1-8B2026.0552.615.95
AFlowModel=Llama-3.1-8B2026.0547.516.4
AutoFlowModel=Llama-3.1-8B2026.0546.818.1
AgentKBModel=Llama-3.1-8B2026.0546.518.55
TaskWeaverModel=Llama-3.1-8B2026.0545.220.22
LLMCompilerModel=Llama-3.1-8B2026.0544.715.05
GraphFlowModel=Gemma-2-9B2026.0542.513.1
MetaGPTModel=Llama-3.1-8B2026.0542.314.68
AgentKBModel=Gemma-2-9B2026.0537.515.85
AFlowModel=Gemma-2-9B2026.0537.215.35
AutoFlowModel=Gemma-2-9B2026.0536.916.8
VanillaModel=Llama-3.1-8B2026.0536.612.58
LLMCompilerModel=Gemma-2-9B2026.0535.214.35
TaskWeaverModel=Gemma-2-9B2026.0534.818.5
MetaGPTModel=Gemma-2-9B2026.0534.612.87
VanillaModel=Gemma-2-9B2026.0530.67.99