MEGA-Bench Task - GUI Act Mobile Swipe: leaderboard
The "GUI Act Mobile Swipe" subtask of MEGA-Bench Task. A single task from MEGA-Bench, a large-scale multimodal evaluation suite that scores vision-language models across 500+ real-world tasks spanning perception, reasoning, OCR, charts, documents, and multi-image understanding.
Metric: Task Score (%). Source: huggingface.co. Saturation forecast: Not forecast. 44 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL3-78B | 63.4 | #352 |
| 2 | Gemini 1.5 Pro (002) | 62 | #349 |
| 3 | InternVL2.5-78B | 60.5 | #431 |
| 4 | InternVL2-8B | 60.2 | #817 |
| 5 | GPT-4o | 59.3 | #343 |
| 6 | InternVL3-14B | 58.4 | #505 |
| 7 | Claude 3.5 Sonnet (20241022) | 57.5 | #291 |
| 8 | Pixtral-12B | 57.1 | #808 |
| 9 | MiniCPM-V-2.6 | 57 | #836 |
| 10 | Qwen 2 VL 2B | 57 | #1220 |
| 11 | Claude 3.5 Sonnet (20240620) | 54.9 | #299 |
| 12 | InternVL3-8B | 54.5 | #620 |
| 13 | InternVL3-38B | 54.1 | #405 |
| 14 | Llama 4 Scout Base | 53.5 | #707 |
| 15 | Gemini 2.0 Flash (Preview) | 53.2 | #370 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-gui-act-mobile-swipe · How It Works · Data refreshed daily, snapshot 2026-10-20.