Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Task Decomposition on 3D-LLM Held-In 1.0 (test)
Loading...
43.8
BLEU-1
Agentic Collaborative Cognition
24.768
29.709
34.65
39.591
Jun 23, 2026
BLEU-1
BLEU-4
METEOR
ROUGE
Updated 1mo ago
Evaluation Results
Method
Method
Links
BLEU-1
BLEU-4
METEOR
ROUGE
Agentic Collaborative Cognition
Supervision=Zero-shot
2026.06
43.8
24.9
21
48.8
Agent3D-Zero
Supervision=Zero-shot
2026.06
42
15.5
22.9
45.1
3D-LLM
Supervision=Fully Supe...
2026.06
33.9
7.4
15.9
37.8
flamingo
Supervision=Fully Supe...
2026.06
33.1
7.3
16.1
33.2
BLIP2-flant5
Supervision=Fully Supe...
2026.06
33.1
6.9
15.5
34
flant5
Supervision=Fully Supe...
2026.06
25.5
6
13.9
28.4
Feedback
Search any
task
Search any
task