AI Paper Atlas

Research map / Benchmarks / ScreenSpot-Pro

ScreenSpot-Pro leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ScreenSpot-Pro. Best accuracy: 74 (Qwen3VL-32B-Instruct + MVP, CVPR 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

ScreenSpot-Pro · accuracy

11 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
174Qwen3VL-32B-Instruct + MVPMVP: Multiple View Prediction Improves GUI Grounding
CVPR 2026 · Table 1
3D generation
261.1MolmoPoint-GUI-8B (64crops)Molmo-Point: Better Pointing for VLMs with Grounding Tokens
ECCV 2026 · Table 3
Multimodal LLMs
360.8OpenCUA-72B
Qwen2.5-VL-72B
OpenCUA: Open Foundations for Computer-Use Agents
NeurIPS 2025 · Table: GUI grounding results
Agents, code and math
460.7GUI-SD
Qwen3-VL-Instruct-8B
Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding
NeurIPS 2026 · Table 2
Reasoning and chain of thought
553.8GUI-AIMA-3B
Qwen2.5-VL-3B
GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding
ECCV 2026 · Table 1
Multimodal LLMs
652.9GroundNext-7B (RL)
Qwen2.5-VL-7B
Grounding Computer Use Agents on Human Demonstrations
ICLR 2026 · Table 2
LLM agents
751.9InfiGUI-G1-7B
Qwen2.5-VL-7B-Instruct
InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization
AAAI 2026 · Table 1
RL from feedback
848.3FocusUI-7B (r=100%)
Qwen2.5-VL-7B
FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection
CVPR 2026 · Table 1
Multimodal LLMs
947.5GUI-G2-7B
Qwen2.5-VL-7B-Instruct
GUI-G²: Gaussian Reward Modeling for GUI Grounding
AAAI 2026 · Table 1
RL from feedback
1044.8GUI-Eyes-3B
Qwen2.5-VL-3B
GUI-Eyes: Tool-Augmented Perception for Visual Grounding in GUI Agents
AAAI 2026 · Table 1
Multimodal LLMs
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.