Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
3D-assisted Dialog on 3D-LLM Held-In Dataset 1.0 (test)
Loading...
47.4
BLEU-1
Agentic Collaborative Cognition
26.6
32
37.4
42.8
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
47.4
24
28.6
47.3
3D-LLM
Supervision=Fully Supe...
2026.06
39
16.6
18.9
39.3
Agent3D-Zero
Supervision=Zero-shot
2026.06
32.8
9.8
19.3
39.3
BLIP2-flant5
Supervision=Fully Supe...
2026.06
32.4
9.5
11
29.5
flamingo
Supervision=Fully Supe...
2026.06
30.6
9.1
10.4
27.9
flant5
Supervision=Fully Supe...
2026.06
27.4
8.7
9.5
27.5
Feedback
Search any
task
Search any
task