ScreenAI 5B (4.62 B params, w/ OCR)

Reported on 3 benchmarks across 2 tasks · 1 paper

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

Natural Language Processing2 results

Visual Question Answering (VQA)onInfographicVQA
ANLS· uses extra data· 2024-02-07
65.9
best: 80.3 (Gemini Ultra (pixel only))
ScreenAI: A Vision-Language Model for UI and Infographics Understanding arXiv:2402.04615
Visual Question Answering (VQA)onChartQA
1:1 Accuracy· uses extra data· 2024-02-07
76.7
best: 81.3 (ChartPaLI-5B + PaLM 2-S)
ScreenAI: A Vision-Language Model for UI and Infographics Understanding arXiv:2402.04615

Computer Code1 result

Chart Question AnsweringonChartQA
1:1 Accuracy· uses extra data· 2024-02-07
76.7
best: 81.3 (ChartPaLI-5B + PaLM 2-S)
ScreenAI: A Vision-Language Model for UI and Infographics Understanding arXiv:2402.04615