ScreenSpot-Pro

ScreenSpot-Pro - Benchmark Leaderboard & Model Performance | AI Stats

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
Anthropic	Claude Opus 4.7	16 Apr 2026	87.60%	With tools	Yes	Source
OpenAI	GPT 5.2 Chat	11 Dec 2025	86.30%	inferred alias from gpt-5.2-2025-12-11	Yes	Source
Meta	Muse Spark	08 Apr 2026	84.10%	UI localization	Yes	Source
Google	Gemini 3 Pro Preview	18 Nov 2025	72.70%	-	Yes	Source
Google	Gemini 3 Pro Image Preview (Nano Banana Pro)	20 Nov 2025	72.70%	inferred modality/version alias from gemini-3-pro-preview	Yes	Source
Qwen	Qwen 3.5 122B A10B	24 Feb 2026	70.40%	-	Yes	Source
Qwen	Qwen 3.5 Flash	23 Feb 2026	70.30%	inferred family alias from qwen3.5-27b (score=0.4147; benches=81)	Yes	Source
Qwen	Qwen 3.5 27B	24 Feb 2026	70.30%	-	Yes	Source
Google	Gemini 3 Flash Preview	17 Dec 2025	69.10%	-	Yes	Source
Qwen	Qwen 3.5 35B A3B	24 Feb 2026	68.60%	-	Yes	Source
Qwen	Qwen 3.6 Plus	01 Apr 2026	68.20%	-	Yes	Source
Qwen	Qwen 3 VL 235B A22B Instruct	-	62%	-	Yes	-
Qwen	Qwen 3 VL 235B A22B Thinking	-	61.80%	-	Yes	-
Qwen	Qwen 3 VL 30B A3B Instruct	-	60.50%	-	Yes	-
Qwen	Qwen 3 VL 4B Instruct	-	59.50%	-	Yes	-
Qwen	Qwen 3 VL 32B Instruct	-	57.90%	-	Yes	-
Qwen	Qwen 3 VL 30B A3B Thinking	-	57.30%	-	Yes	-
Qwen	Qwen 3 VL 32B Thinking	-	57.10%	-	Yes	-
Qwen	Qwen 3 VL 8B Instruct	-	54.60%	-	Yes	-
Qwen	Qwen 3 4B SafeRL	-	49.20%	inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	-
Qwen	Qwen 3 Reranker 4B	-	49.20%	inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	-
Qwen	Qwen 3 VL 4B Thinking	-	49.20%	-	Yes	-
Qwen	Qwen 3 4B Thinking 2507	-	49.20%	inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48)	Yes	-
Qwen	Qwen 3 Embedding 4B	-	49.20%	inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	-
Qwen	Qwen 3 Guard Gen 4B	-	49.20%	inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48)	Yes	-
Qwen	Qwen 3 4B Instruct 2507	-	49.20%	inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48)	Yes	-
Qwen	Qwen 3 Guard Stream 4B	-	49.20%	inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48)	Yes	-
Qwen	Qwen 3 Guard Gen 8B	-	46.60%	inferred family alias from qwen3-vl-8b-thinking (score=0.3400; benches=50)	Yes	-
Qwen	Qwen 3 8B	-	46.60%	inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50)	Yes	-
Qwen	Qwen 3 Reranker 8B	-	46.60%	inferred family alias from qwen3-vl-8b-thinking (score=0.3850; benches=50)	Yes	-
Qwen	Qwen 3 Embedding 8B	-	46.60%	inferred family alias from qwen3-vl-8b-thinking (score=0.3850; benches=50)	Yes	-
Qwen	Qwen 3 Guard Stream 8B	-	46.60%	inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50)	Yes	-
Qwen	Qwen 3 VL Reranker 8B	-	46.60%	inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50)	Yes	-
Qwen	Qwen 3 VL 8B Thinking	-	46.60%	-	Yes	-
Qwen	Qwen 3 VL Embedding 8B	-	46.60%	inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50)	Yes	-
Qwen	Qwen 2.5 Math 72B	-	43.60%	inferred high-confidence family alias from qwen2.5-vl-72b (score=0.4700; benches=30)	Yes	Source
Qwen	Qwen 2.5 Math RM 72B	-	43.60%	inferred family alias from qwen2.5-vl-72b (score=0.4092; benches=30)	Yes	Source
Qwen	Qwen 2.5 VL 72B Instruct	-	43.60%	-	Yes	Source
Qwen	Qwen 2.5 Math PRM 72B	-	43.60%	inferred family alias from qwen2.5-vl-72b (score=0.4050; benches=30)	Yes	Source
Qwen	Qwen 2.5 Coder 32B Instruct	-	39.40%	inferred high-confidence family alias from qwen2.5-vl-32b (score=0.4641; benches=28)	Yes	Source
Qwen	Qwen 2.5 VL 3B Instruct	-	39.40%	inferred high-confidence family alias from qwen2.5-vl-32b (score=0.4914; benches=28)	Yes	Source
Qwen	Qwen 2.5 VL 32B Instruct	-	39.40%	-	Yes	Source
Qwen	Qwen 2.5 0.5B	-	29%	inferred family alias from qwen2.5-vl-7b (score=0.3131; benches=32)	Yes	Source
Qwen	Qwen 2.5 1.5B	-	29%	inferred family alias from qwen2.5-vl-7b (score=0.3131; benches=32)	Yes	Source
Qwen	Qwen 2.5 3B	-	29%	inferred family alias from qwen2.5-vl-7b (score=0.3531; benches=32)	Yes	Source
Qwen	Qwen 2.5 VL 7B Instruct	-	29%	-	Yes	Source

Recorded Results

Average Score

Score Range

Leading Model

Models Using This Benchmark