MEGA-Bench Task - MMSoc Memotion: leaderboard
The "MMSoc Memotion" 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. 44 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Aquila-VL-2B | 68.2 | #1238 |
| 2 | Llama 3.2 11B | 68.2 | #1199 |
| 3 | InternVL3-38B | 65.9 | #405 |
| 4 | Qwen 2 VL 2B | 65.9 | #1220 |
| 5 | MiniCPM-V-2.6 | 64.7 | #836 |
| 6 | InternVL3-14B | 64.7 | #505 |
| 7 | InternVL2.5-78B | 64.7 | #431 |
| 8 | Gemma 3 4B (IT) | 63.5 | #992 |
| 9 | Qwen 2 VL 7B | 63.5 | #750 |
| 10 | Llama 4 Scout Base | 63.5 | #707 |
| 11 | Gemma 3 12B (IT) | 61.2 | #664 |
| 12 | Gemini 1.5 Pro (002) | 61.2 | #349 |
| 13 | Gemini 2.5 Pro (Preview 03-25) | 61.2 | #123 |
| 14 | GLM-4.1V-9B (Thinking) | 61.2 | #472 (GLM-4.1V-9B) |
| 15 | Gemini 2.0 Flash (Preview) | 61.2 | #370 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-mmsoc-memotion · How It Works · Data refreshed daily, snapshot 2026-10-20.