List your company

Tool Use on Single-Calculator

99.62R-F1MedCalc-Pro Agent Framework
71.186478.568285.9593.3318Jul 3, 2026

Evaluation results

MethodLinks
MedCalc-Pro Agent FrameworkModel=gpt-oss-120b2026.0799.6253.5680.15
MedCalc-Pro Agent FrameworkModel=DeepSeek-V3.12026.0798.5356.1976.04
MedCalc-Pro Agent FrameworkModel=Qwen3-235B-A22B2026.0798.1252.8479.58
MedCalc-Pro Agent FrameworkModel=MedResearcher-R1-32B2026.0798.0340.7677
MedCalc-Pro Agent FrameworkModel=GPT-5-mini2026.0793.1341.1970.13
MedCalc-Pro Agent FrameworkModel=Llama-3.3-70B-Instruct2026.0786.6337.0365.94
MedRaCModel=gpt-oss-120b2026.0786.5743.9275.38
MedRaCModel=Qwen3-235B-A22B2026.0786.5742.3573.85
MedRaCModel=Llama-3.3-70B-Instruct2026.0786.5734.0569.37
MedRaCModel=GPT-5-mini2026.0786.5744.776.72
MedRaCModel=DeepSeek-V3.12026.0786.5739.0569.08
MedRaCModel=MedResearcher-R1-32B2026.0786.5740.4264.5
MeNTiModel=gpt-oss-120b2026.0786.1137.5658.4
MeNTiModel=MedResearcher-R1-32B2026.0785.5141.2555.73
MeNTiModel=Llama-3.3-70B-Instruct2026.0784.5338.3558.49
MeNTiModel=Qwen3-235B-A22B2026.0782.9143.557.92
MeNTiModel=GPT-5-mini2026.0782.3545.6656.11
ReActModel=MedResearcher-R1-32B2026.0780.2140.4256.49
ReActModel=gpt-oss-120b2026.0779.548.0155.06
ReActModel=DeepSeek-V3.12026.0778.0346.6555.06
ReActModel=GPT-5-mini2026.0777.935.4749.05
ReActModel=Qwen3-235B-A22B2026.0775.5139.3651.34
MeNTiModel=DeepSeek-V3.12026.0773.5639.0949.71
ReActModel=Llama-3.3-70B-Instruct2026.0772.2823.2640.84