List your company

Error Detection on CoSPlan

9.1Robo-VQA-E ScoreCoT
7.16820.20933.2546.291Dec 11, 2025

Evaluation results

MethodLinks
CoTVLM=Qwen2 VL-8B2025.129.120.830.6
VanillaVLM=Qwen2 VL-8B2025.129.220.532.3
SGVLM=Qwen2 VL-8B2025.129.620.735.2
SGIVLM=Qwen2 VL-8B2025.1210.121.335.7
Random2025.1215.433.333.3
VanillaVLM=Janus-pro-7B2025.1217.520.529.3
CoTVLM=Janus-pro-7B2025.1218.119.131
VanillaVLM=Intern-VLM2025.1224.332.836.5
CoTVLM=Intern-VLM2025.1225.233.137.9
SGVLM=Janus-pro-7B2025.1226.12127.6
SGVLM=Intern-VLM2025.1226.133.437.3
SGIVLM=Janus-pro-7B2025.1227.621.633.2
SGIVLM=Intern-VLM2025.1231.534.842.9
VanillaVLM=CoG-VLM2025.1232.16.441.3
CoTVLM=CoG-VLM2025.1233.48.443.1
SGVLM=CoG-VLM2025.1235.313.344.5
SGIVLM=CoG-VLM2025.1238.71146.1
SGVLM=GPT-4o2025.1244.235.342.1
CoTVLM=GPT-4o2025.1245.340.335.1
SGIVLM=GPT-4o2025.1257.441.150.7