flin775/GTA1-7B-AWQ

This model is covnert from HelloKKMe/GTA1-7B by AutoAwq.

Model Description

GTA1-7B is an agent-grounding model that achieves state-of-the-art performance across a variety of GUI benchmarks.

Paper: GTA1: GUI Test-time Scaling Agent

Github: https://github.com/Yan98/GTA1

Model	Size	Open Source	ScreenSpot-V2	ScreenSpotPro	OSWORLD-G
OpenAI CUA	—	❌	87.9	23.4	—
Claude 3.7	—	❌	87.6	27.7	—
JEDI-7B	7B	✅	91.7	39.5	54.1
SE-GUI	7B	✅	90.3	47.0	—
UI-TARS	7B	✅	91.6	35.7	47.5
UI-TARS-1.5*	7B	✅	89.7*	42.0*	64.2*
UGround-v1-7B	7B	✅	—	31.1	36.4
Qwen2.5-VL-32B-Instruct	32B	✅	91.9*	48.0	59.6*
UGround-v1-72B	72B	✅	—	34.5	—
Qwen2.5-VL-72B-Instruct	72B	✅	94.00*	53.3	62.2*
UI-TARS	72B	✅	90.3	38.1	—
GTA1 (Ours)	7B	✅	92.4 (∆ +2.7)	50.1(∆ +8.1)	67.7 (∆ +3.5)
GTA1 (Ours)	32B	✅	93.2 (∆ +1.3)	53.6 (∆ +5.6)	61.9(∆ +2.3)
GTA1 (Ours)	72B	✅	94.8(∆ +0.8)	58.4 (∆ +5.1)	66.7(∆ +4.5)

Note:

• Model size is indicated in billions (B) of parameters.
• A dash (—) denotes results that are currently unavailable.
• A superscript asterisk (﹡) denotes our evaluated result.
• UI-TARS-1.5 7B, Qwen2.5-VL-32B-Instruct, and Qwen2.5-VL-72B-Instruct are applied as our baseline models.
• ∆ indicates the performance improvement (∆) of our model compared to its baseline.