Fara-7B: An Efficient Agentic Model for Computer Use
Open paper
Benchmark
Model
Rank
Results
computer-use-agents-on-online-mind2web
Fara-7B
#8
Success Rate: 34.1
natural-language-visual-grounding-on-screenspot
Fara-7B
#14
Accuracy (%): 86.7
computer-use-agents-on-screenspot-v2
Fara-7B
#38
Accuracy: 89.3
Rank counts only results with a code link.