List your company

Medical Question Answering on MedMCQA (Generation Metrics)

10.82BLEU ScoreLlama-3.1-8B-Instruct
-0.4122.5045.428.336Mar 18, 2026

Evaluation results

MethodLinks
Llama-3.1-8B-InstructSFT Dataset=10k Unknown2026.0310.8236.5525.9788.49
glm4-9b-chatSFT Dataset=10k Unknown2026.039.8236.0225.588.3
Mistral-7B-Instruct-v0.1SFT Dataset=10k Unknown2026.039.7136.1125.288.37
Mistral-7B-Instruct-v0.3SFT Dataset=10k Unknown2026.039.5835.2825.0888.3
Llama-3.1-8B-InstructSFT Dataset=10k Augmented2026.038.8130.5421.3687.31
Llama-3.1-8B-InstructSFT Dataset=5k Unknown2026.038.4929.9620.8487.2
glm4-9b-chatSFT Dataset=10k Augmented2026.038.4829.9221.6787.13
Phi-3.5-mini-instructSFT Dataset=10k Augmented2026.038.329.1820.0587.07
Mistral-7B-Instruct-v0.3SFT Dataset=10k Augmented2026.038.2428.9420.8687.07
Llama-3.1-8B-InstructSFT Dataset=10k Combine2026.038.2130.1721.1187.14
Phi-3.5-mini-instructSFT Dataset=10k Unknown2026.038.0529.6919.9587.21
Llama-2-7b-chat-hfSFT Dataset=10k Unknown2026.037.9929.7820.1487.15
Phi-3.5-mini-instructSFT Dataset=5k Unknown2026.037.6127.8518.5986.81
Mistral-7B-Instruct-v0.1SFT Dataset=10k Augmented2026.037.4328.8520.2986.92
Phi-3.5-mini-instructSFT Dataset=10k Combine2026.037.4227.718.5786.74
Mistral-7B-Instruct-v0.1SFT Dataset=10k Combine2026.037.0627.8619.1686.7
Mistral-7B-Instruct-v0.1SFT Dataset=5k Unknown2026.036.9727.3318.8286.65
glm4-9b-chatSFT Dataset=10k Combine2026.036.928.2719.6786.8
Mistral-7B-Instruct-v0.3SFT Dataset=10k Combine2026.036.8827.5519.2986.76
Qwen2.5-7B-InstructSFT Dataset=5k Unknown2026.036.824.0716.5885.95
Mistral-7B-Instruct-v0.3SFT Dataset=5k Unknown2026.036.7127.0218.7986.63
Phi-3.5-mini-instructSFT Dataset=5k Known2026.036.6325.416.986.3
Qwen2.5-7B-InstructSFT Dataset=10k Unknown2026.036.6327.1618.7986.54
glm4-9b-chatSFT Dataset=5k Unknown2026.036.6128.4419.8786.73
Qwen2.5-7B-InstructSFT Dataset=10k Combine2026.036.324.1316.885.93
Qwen2.5-7B-InstructSFT Dataset=10k Augmented2026.035.9224.6517.7386.14
Llama-2-7b-chat-hfSFT Dataset=5k Unknown2026.035.9123.2515.5485.79
Llama-3.1-8B-InstructSFT Dataset=5k Known2026.035.7223.2916.1885.71
Llama-2-7b-chat-hfSFT Dataset=10k Augmented2026.035.5623.7716.0685.92
Qwen1.5-7B-ChatSFT Dataset=10k Unknown2026.035.4623.7215.7885.84
Llama-2-7b-chat-hfSFT Dataset=10k Combine2026.035.3723.7615.885.9
Qwen1.5-7B-ChatSFT Dataset=10k Augmented2026.034.8521.5514.8485.4
Qwen2.5-7B-InstructSFT Dataset=5k Known2026.034.6720.313.8585.06
Qwen1.5-7B-ChatSFT Dataset=10k Combine2026.034.619.6513.1285
Mistral-7B-Instruct-v0.3SFT Dataset=5k Known2026.034.3219.1713.1185.03
glm4-9b-chatSFT Dataset=5k Known2026.034.1720.6213.8685.17
Qwen1.5-7B-ChatSFT Dataset=5k Unknown2026.034.1319.3412.8684.9
Mistral-7B-Instruct-v0.1SFT Dataset=5k Known2026.033.3518.0912.0384.74
Llama-2-7b-chat-hfSFT Dataset=5k Known2026.033.3416.1310.4584.35
Qwen1.5-7B-ChatSFT Dataset=5k Known2026.033.1115.099.9584.1
DeepSeek-R1-Distill-Qwen-7BSFT Dataset=10k Unknown2026.032.8514.539.284
DeepSeek-R1-Distill-Qwen-7BSFT Dataset=10k Augmented2026.032.6213.558.9184
DeepSeek-R1-Distill-Qwen-7BSFT Dataset=10k Combine2026.032.4412.557.9283.7
DeepSeek-R1-Distill-Qwen-7BSFT Dataset=5k Unknown2026.031.9111.997.5483.62
DeepSeek-R1-Distill-Qwen-7BSFT Dataset=5k Known2026.031.8510.416.583.19
Mistral-7B-Instruct-v0.1SFT Dataset=None2026.030.123.176.2979.6
Mistral-7B-Instruct-v0.3SFT Dataset=None2026.030.112.15.1979.22
Llama-3.1-8B-InstructSFT Dataset=None2026.030.12.345.0178.58
Phi-3.5-mini-instructSFT Dataset=None2026.030.091.594.178.44
Qwen2.5-7B-InstructSFT Dataset=None2026.030.091.84.3478.35
glm4-9b-chatSFT Dataset=None2026.030.081.714.2178.48
Qwen1.5-7B-ChatSFT Dataset=None2026.030.081.644.0378.63
Llama-2-7b-chat-hfSFT Dataset=None2026.030.060.992.5477.33
DeepSeek-R1-Distill-Qwen-7BSFT Dataset=None2026.030.020.521.3176.29