T,Model,b4bqa,b4b,medmcqa_g2b,medmcqa_orig_filtered,medmcqa_diff,medqa_4options_g2b,medqa_4options_orig_filtered,medqa_diff 🔶,"01-ai-Yi-1.5-34B",85.16,75.37,59.77,69.25,-9.48,59.79,64.55,-4.76 🔶,"aaditya-Llama3-OpenBioLLM-70B",85.1,78.76,63.22,73.85,-10.63,70.9,75.4,-4.5 🔶,"CohereForAI-aya-23-35B",78.4,65.72,48.56,52.87,-4.31,47.88,51.06,-3.18 💬,"CohereForAI-c4ai-command-r-plus",84.93,72.41,49.14,61.49,-12.35,56.61,60.32,-3.71 🔶,"johnsnowlabs-JSL-MedLlama-3-8B-v9",75.17,74.45,64.08,77.01,-12.93,70.63,82.01,-11.38 🟢,"meta-llama-Llama-2-70B-hf",77.01,65.63,45.98,52.3,-6.32,52.65,55.03,-2.38 🟢,"meta-llama-Llama-2-7b-hf",36.83,36.0,33.91,34.2,-0.29,34.39,37.3,-2.91 🟢,"meta-llama-Meta-Llama-3-70B",90.12,82.55,66.67,78.16,-11.49,72.75,75.13,-2.38 🟢,"meta-llama-Meta-Llama-3-8B",82.7,71.21,52.87,59.2,-6.33,55.03,60.85,-5.82 🟢,"microsoft-phi-1_5",28.01,30.24,31.61,30.46,1.15,34.92,34.66,0.26 🟢,"microsoft-phi-1",19.64,21.18,24.14,25.86,-1.72,21.69,20.9,0.79 🟢,"microsoft-phi-2",47.49,44.79,37.64,42.24,-4.6,41.8,43.92,-2.12 💬,"microsoft-Phi-3-medium-4k-instruct",69.98,65.94,60.34,72.41,-12.07,53.44,58.47,-5.03 🟢,"mistralai-Mistral-7B-v0.3",70.31,61.99,48.28,56.9,-8.62,48.68,53.17,-4.49 🟢,"mistralai-Mixtral-8x22B-v0.1",87.72,78.82,61.78,70.4,-8.62,67.46,71.43,-3.97 🟢,"mistralai-Mixtral-8x7B-v0.1",86.1,74.75,55.46,64.94,-9.48,60.05,62.43,-2.38 🔶,"ProbeMedicalYonseiMAILab-medllama3-v20",71.93,74.75,65.23,80.17,-14.94,76.46,90.21,-13.75 🟢,"Qwen-Qwen2-72B",91.02,83.72,71.55,77.87,-6.32,74.07,75.4,-1.33 🟢,"Qwen-Qwen2-7B",80.41,70.28,55.17,63.51,-8.34,53.7,58.99,-5.29 💬,"GPT-4",94.92,,88.79,91.67,-2.88,89.95,92.33,-2.38 💬,"GPT-4o",96.48,,86.49,90.52,-4.03,88.36,90.21,-1.85 💬,"GPT-3.5 Turbo",91.74,,97.7,98.28,-0.58,96.03,96.3,-0.27 💬,"Claude Opus",92.19,,79.89,86.49,-6.6,83.33,85.71,-2.38 💬,"Gemini 1.5 Pro",0.0,,82.47,86.49,-4.02,87.3,88.62,-1.32 💬,"Gemini Pro 1",0.0,,73.85,68.1,5.75,73.02,70.63,2.39 💬,"Gemini 1.5 Flash",0.0,,94.83,97.41,-2.58,96.03,97.09,-1.06