VECTOR WIREAI INTELLIGENCE
⌘K
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models —Deals —Regulatory —Sources —

screenspot_pro_no_tools

30 models tracked

ScreenSpot-Pro — No-tools condition of ScreenSpot-Pro GUI-grounding benchmark; distinct from with-tools condition.

#ModelVendorBest scoreRunsLast seen
1Claude Opus 4.8Anthropic87.922026-08-23
2GPT-5.2OpenAI86.312026-08-23
3Qwen3.8 Max PreviewAlibaba84.512026-08-23
4Muse SparkMeta84.112026-08-23
5Claude Opus 4.7Anthropic79.532026-06-21
6Qwen3.7 Plus PreviewAlibaba7912026-08-23
7muse-glimmer-30bMeta75.412026-08-23
8Gemini 3 ProGoogle72.712026-08-23
9Qwen3.5 122B A10BAlibaba70.412026-08-23
10Qwen3.5 27BAlibaba70.312026-08-23
11Gemini 3 Flash PreviewGoogle69.112026-08-23
12Qwen3.5 35B A3BAlibaba68.612026-08-23
13Qwen3.6 PlusAlibaba68.212026-08-23
14Qwen3 VL 235B A22B InstructAlibaba6212026-08-23
15Qwen3 VL 235B A22B ReasoningAlibaba61.812026-08-23
16Qwen3 VL 30B A3B InstructAlibaba60.512026-08-23
17Qwen3 VL 4B InstructAlibaba59.512026-08-23
18Qwen3 VL 32B InstructAlibaba57.912026-08-23
19Claude Opus 4.6Anthropic57.722026-06-21
20Qwen3 VL 30B A3B ReasoningAlibaba57.312026-08-23
21Qwen3 VL 32B ReasoningAlibaba57.112026-08-23
22Qwen3 VL 8B InstructAlibaba54.612026-08-23
23Step3 VL 10BStepFun51.522026-06-05
24Qwen3 VL 4B (Reasoning)Alibaba49.212026-08-23
25Qwen3 VL Thinking (8B)Alibaba46.632026-08-23
26GLM-4.6V-Flash (9B)Z.ai45.722026-06-05
27Qwen2.5 VL 72BAlibaba43.612026-08-23
28Qwen2.5 VL 32BAlibaba39.412026-08-23
29MiMo VL RL 2508 (7B)Xiaomi34.822026-06-05
30InternVL-3.5 (8B)OpenGVLab15.422026-06-05

Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.