MindAct-780M

Reported on 4 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Conversational Web NavigationonWebLINX
Element (IoU)· 2024-02-08
13.39
best: 22.82 (Llama-2-13B)
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue arXiv:2402.05930
Conversational Web NavigationonWebLINX
Intent Match· 2024-02-08
75.87
best: 84 (S-LLaMA-2.7B)
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue arXiv:2402.05930
Conversational Web NavigationonWebLINX
Overall score· 2024-02-08
15.13
best: 25.21 (Llama-2-13B)
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue arXiv:2402.05930
Conversational Web NavigationonWebLINX
Text (F1)· 2024-02-08
13.58
best: 27.17 (S-LLaMA-2.7B)
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue arXiv:2402.05930