Multimodal & Grounded benchmark
ScreenSpot Pro leaderboard
Every model the catalog carries a published ScreenSpot Pro value for, ranked by that value.
A GUI-grounding benchmark for 1,581 instructions in full-screen, high-resolution professional interfaces. It tests where a target is, not whether an agent can finish the surrounding workflow.
ScreenSpot Pro ranking
18 models with a published ScreenSpot Pro value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Static interface element localization |
|---|---|---|---|
| 1 |  GPT-6 Astra | OpenAI | 92.7 |
| 2 |  Claude Opus 4.8 | Anthropic | 87.9 |
| 3 | GPT-5.4 | OpenAI | 85.4 |
| 4 |  Qwen3.8 Max | Alibaba | 84.5 |
| 5 |  Gemini 3.1 Pro | 84.4 | |
| 6 |  Muse Spark | Meta | 84.1 |
| 7 | Claude Opus 4.6 | Anthropic | 83.1 |
| 8 | Qwen3.7 Plus | Alibaba | 79.0 |
| 9 | Muse Glimmer 30B | Meta | 75.4 |
| 10 | Gemini 3 Pro | 72.7 | |
| 11 | HCHolo2-235B-A22B | H Company | 70.6 |
| 12 | Qwen3.6 Plus | Alibaba | 68.2 |
| 13 | HCHolo2-30B-A3B | H Company | 66.1 |
| 14 | Qwen3.5 397B | Alibaba | 65.6 |
| 15 | HCHolo2-8B | H Company | 58.9 |
| 16 |  Nemotron 3 Nano Omni 30B A3B | NVIDIA | 57.8 |
| 17 | HCHolo2-4B | H Company | 57.2 |
| 18 | Claude Opus 4.5 | Anthropic | 45.7 |
Evidence key: Observed
Rows are ordered by the value ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.