List your company

Reasoning on Open-R1 (test)

65.83Accuracy (Simple)FedProx
40.838847.326953.81560.3031Jun 2, 2026

Evaluation results

MethodLinks
FedProxModel=Qwen3-4B2026.0665.8344.9814.3741.7
FGRPOModel=Qwen3-4B2026.0665.4745.2918.843.16
SCAFFOLDModel=Qwen3-4B2026.0663.0645.059.2139.08
FedAvgModel=Qwen3-4B2026.0662.8249.378.3840.16
FedAvgModel=Qwen2.5-7B2026.0660.943.7232.7545.78
FedProxModel=Qwen2.5-7B2026.0658.5646.2532.7545.84
SCAFFOLDModel=Qwen2.5-7B2026.0655.9848.1732.6945.6
FGRPOModel=Qwen2.5-7B2026.0655.4450.8736.7747.68
FedAvgModel=Llama-3.2-11B2026.0649.2540.8431.840.62
FGRPOModel=Llama-3.2-11B2026.0649.0741.2635.3341.88
FedProxModel=Llama-3.2-11B2026.0648.8340.2432.0440.36
SCAFFOLDModel=Llama-3.2-11B2026.0648.1742.0433.2941.16
FGRPOModel=Qwen2.5-3B2026.0648.1144.1433.3541.86
FedAvgModel=Qwen2.5-3B2026.0647.6340.2428.0838.64
SCAFFOLDModel=Qwen2.5-3B2026.0646.374327.1938.84
FedProxModel=Qwen2.5-3B2026.0641.842.0424.5536.12