MEGA-Bench Task - App Interactive Operations Alipay: leaderboard
The "App Interactive Operations Alipay" 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: Estimated already saturated. 44 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 76.5 | #123 |
| 2 | Claude 3.5 Sonnet (20241022) | 70.6 | #291 |
| 3 | Claude 3.5 Sonnet (20240620) | 64.7 | #299 |
| 4 | GLM-4.1V-9B (Thinking) | 64.7 | #472 (GLM-4.1V-9B) |
| 5 | Gemini 2.0 Flash (Preview) | 64.7 | #370 |
| 6 | GPT-4o | 58.8 | #343 |
| 7 | Qwen 2 VL 72B | 58.8 | #460 |
| 8 | InternVL2.5-78B | 58.8 | #431 |
| 9 | GPT-4o Mini | 47.1 | #599 |
| 10 | Gemini 1.5 Pro (002) | 41.2 | #349 |
| 11 | Gemini 1.5 Flash (002) | 41.2 | #583 |
| 12 | InternVL3-78B | 29.4 | #352 |
| 13 | MiniCPM-V-2.6 | 29.4 | #836 |
| 14 | Gemma 3 27B (IT) | 23.5 | #523 |
| 15 | Qwen 2 VL 7B | 23.5 | #750 |
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-app-interactive-operations-alipay · How It Works · Data refreshed daily, snapshot 2026-10-20.