List your company

Volumetric Computed Tomography Multiple Choice Question Answering on AMOS-MM-MCQ (OOD)

66.13Existence AccuracyTIF-GRPO w/ Acc Reward (AMOS-MM)
34.233242.514150.79559.0759May 19, 2026

Evaluation results

MethodLinks
TIF-GRPO w/ Acc Reward (AMOS-MM)#Params=4B2026.0566.1376.3295.1574.2469.67
TIF-GRPO w/ Acc Reward (CT-RATE)#Params=4B2026.0558.0656.1486.4163.0566.65
GRPO w/ Acc Reward (AMOS-MM)#Params=4B2026.0557.8368.8691.2667.3463.91
Qwen3-VL-8B#Params=8B2026.0556.119.7461.6548.0250.63
InternVL3.5-8B#Params=8B2026.0554.117.9858.7445.8849.18
GRPO w/ Acc Reward (CT-RATE)#Params=4B2026.0553.4653.5185.4459.8963.59
RadFM#Params=14B2026.0552.5522.8127.6739.139.53
Fleming-VL-8B#Params=8B2026.0552.1138.664.0851.4153.92
CT-CHAT#Params=8B2026.0551.4545.1867.9653.6754.22
GPT-5#Params=*2026.0550.8951.5980.6159.8260.54
Hulu-Med#Params=7B2026.0550.3337.4778.5853.5957.03
Gemini-3-Pro#Params=*2026.0547.3253.1680.6856.4256.7
M3D-LaMed#Params=7B2026.0535.4643.8666.544.8648.72