3D-LLM
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
3D-LLM Task Decomposition
52.2Accuracy
8
3D-LLM 3D-assisted Dialogue
70.6Accuracy
8
3D-LLM Held-In 1.0 (test)
43.8BLEU-1
6
3D-LLM Held-In Dataset 1.0 (test)
47.4BLEU-1
6
Loading the SOTA2 catalog…