MEGA-Bench Task - Web Action Grounding: leaderboard
The "Web Action Grounding" 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 | Gemma 3 27B (IT) | 85.7 | #523 |
| 2 | Claude 3.5 Sonnet (20241022) | 78.6 | #291 |
| 3 | Claude 3.5 Sonnet (20240620) | 78.6 | #298 |
| 4 | InternVL3-78B | 78.6 | #353 |
| 5 | Gemini 2.5 Pro (Preview 03-25) | 78.6 | #123 |
| 6 | Qwen 2 VL 7B | 78.6 | #750 |
| 7 | Qwen 2 VL 72B | 78.6 | #461 |
| 8 | GLM-4.1V-9B (Thinking) | 78.6 | #470 (GLM-4.1V-9B) |
| 9 | InternVL3-38B | 71.4 | #405 |
| 10 | GPT-4o | 64.3 | #343 |
| 11 | GPT-4o Mini | 64.3 | #599 |
| 12 | Gemini 1.5 Pro (002) | 64.3 | #350 |
| 13 | Gemini 2.0 Flash (Preview) | 64.3 | #370 |
| 14 | Llama 4 Scout Base | 64.3 | #707 |
| 15 | InternVL3-14B | 57.1 | #506 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-web-action-grounding · How It Works · Data refreshed daily, snapshot 2026-10-21.