Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Video Question Answering on EgoThink
Loading...
76
Affordance Score
GPT-5.2
45.84
53.67
61.5
69.33
May 30, 2026
Affordance Score
Assistance Score
Attribute Score
Situated Score
Location Score
Updated 1d ago
Evaluation Results
Method
Method
Links
Affordance Score
Assistance Score
Attribute Score
Situated Score
Location Score
GPT-5.2
2026.05
76
69
85
73
92
GPT-4o
2026.05
67
46
75
70
72
Ours FT (4B)
Fine-tuning=Yes, Model...
2026.05
65
47
84
84
89
Baseline (Qwen3-VL-4B)
Fine-tuning=No, Model...
2026.05
52
40
78
79
86
Qwen3-VL-235B
Model Scale=235B
2026.05
47
46
86
89
96
Feedback
Search any
task
Search any
task