# ScreenSpot Pro leaderboard

Multimodal & Grounded benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/multimodal-grounded-screen-spot-pro

Every model the catalog carries a published ScreenSpot Pro value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Static interface element localization |
| Tasks | 1,581 grounding instructions |
| Difficulty | Professional GUI grounding |
| Published by | [ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use](https://arxiv.org/abs/2504.07981) |

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

22 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 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 92.7 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Opus 4.8](https://modelscale.dev/models/claude-opus-4-8) | Anthropic | 87.9 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GPT-5.4](https://modelscale.dev/models/gpt-5-4) | OpenAI | 85.4 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Qwen3.8 Max](https://modelscale.dev/models/qwen3-8-max) | Alibaba | 84.5 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Gemini 3.1 Pro](https://modelscale.dev/models/gemini-3-1-pro) | Google | 84.4 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Muse Spark](https://modelscale.dev/models/muse-spark) | Meta | 84.1 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Inkling 2 Small](https://modelscale.dev/models/inkling-2-small) | Thinking Machines Lab | 83.8 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Claude Opus 4.6](https://modelscale.dev/models/claude-opus-4-6) | Anthropic | 83.1 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Qwen3.7 Plus](https://modelscale.dev/models/qwen3-7-plus) | Alibaba | 79.0 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Inkling 2 Mini](https://modelscale.dev/models/inkling-2-mini) | Thinking Machines Lab | 76.5 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Muse Glimmer 30B](https://modelscale.dev/models/muse-glimmer-30b) | Meta | 75.4 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Gemini 3 Pro](https://modelscale.dev/models/gemini-3-pro) | Google | 72.7 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Holo2-235B-A22B](https://modelscale.dev/models/holo2-235b-a22b) | H Company | 70.6 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Qwen3.6 Plus](https://modelscale.dev/models/qwen3-6-plus) | Alibaba | 68.2 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Holo2-30B-A3B](https://modelscale.dev/models/holo2-30b-a3b) | H Company | 66.1 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Qwen3.5 397B](https://modelscale.dev/models/qwen3-5-397b) | Alibaba | 65.6 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Qwen3-VL-235B-A22B Instruct](https://modelscale.dev/models/qwen3-vl-235b-a22b-instruct) | Alibaba | 62.0 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Holo2-8B](https://modelscale.dev/models/holo2-8b) | H Company | 58.9 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Nemotron 3 Nano Omni 30B A3B](https://modelscale.dev/models/nemotron-3-nano-omni-30b-a3b) | NVIDIA | 57.8 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Holo2-4B](https://modelscale.dev/models/holo2-4b) | H Company | 57.2 | Observed 2026-11-21 · source benchlm:models |
| 21 | [LFM3-VL-2B](https://modelscale.dev/models/lfm3-vl-2b) | LiquidAI | 55.5 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 45.7 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
