ALL Bench Multimodal — leaderboard
Composite multimodal leaderboard aggregating model results across VLM, image generation, video generation, and agent-style multimodal evaluations.
Metric: Average Numeric VLM Score (%). Source: huggingface.co. Status: saturated. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 86.7 |
| 2 | Claude Opus 4.6 | 85.1 |
| 3 | GPT-5 | 84.2 |
| 4 | Gemini 3 Flash | 83.8 |
| 5 | Gemini 3 Pro | 83.75 |
| 6 | Gemini 3.1 Pro (Preview) | 82 |
| 7 | InternVL3-78B | 79.74 |
| 8 | Qwen 3.5 9B | 71.32 |
| 9 | Qwen 3.5 4B | 68.72 |
| 10 | GPT-5 Nano | 55.24 |
Interactive version: theaggregate.ai/benchmark?slug=all-bench-multimodal · How the rankings work · Data refreshed daily, snapshot 2026-07-22.