MEGA-Bench Task - ActivityNetQA: leaderboard
The "ActivityNetQA" 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 | GPT-4o | 70.5 | #343 |
| 2 | Qwen 2 VL 72B | 58.9 | #460 |
| 3 | GLM-4.1V-9B (Thinking) | 53.7 | #472 (GLM-4.1V-9B) |
| 4 | Aquila-VL-2B | 51.6 | #1238 |
| 5 | Gemini 1.5 Flash (002) | 50.5 | #583 |
| 6 | InternVL2.5-78B | 49.5 | #431 |
| 7 | InternVL3-14B | 48.4 | #505 |
| 8 | Qwen 2 VL 2B | 47.9 | #1220 |
| 9 | Gemma 3 27B (IT) | 45.8 | #523 |
| 10 | InternVL3-78B | 45.8 | #352 |
| 11 | InternVL2.5-2B | 45.3 | #1249 |
| 12 | Gemini 1.5 Pro (002) | 44.7 | #349 |
| 13 | Gemini 2.0 Flash (Preview) | 44.7 | #370 |
| 14 | Qwen 2 VL 7B | 44.5 | #750 |
| 15 | InternVL2-8B | 43.2 | #817 |
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-activitynetqa · How It Works · Data refreshed daily, snapshot 2026-10-20.