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

#ModelScore
1GPT-5.286.7
2Claude Opus 4.685.1
3GPT-584.2
4Gemini 3 Flash83.8
5Gemini 3 Pro83.75
6Gemini 3.1 Pro (Preview)82
7InternVL3-78B79.74
8Qwen 3.5 9B71.32
9Qwen 3.5 4B68.72
10GPT-5 Nano55.24

Interactive version: theaggregate.ai/benchmark?slug=all-bench-multimodal · How the rankings work · Data refreshed daily, snapshot 2026-07-22.