Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Step Completion on CoSPlan Robo-VQA-E

52.2Accuracy

GPT-4o

10.91221.63132.3543.069Dec 11, 2025
Updated 3mo ago

Evaluation Results

MethodLinks
2025.12
52.2
2025.12
48.2
2025.12
25.1
2025.12
23.5
2025.12
22.1
2025.12
21.5
2025.12
21.3
2025.12
20
2025.12
18.9
2025.12
17.6
2025.12
17.1
2025.12
14.7
2025.12
14.1
2025.12
13.1
2025.12
12.5