OmniGAIA: leaderboard
Omni-modal general AI assistant benchmark for long-horizon agents using vision, audio, language, web search, browser, and code-execution tasks.
Metric: Overall Accuracy (%). Source: huggingface.co. Status: saturation imminent. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 62.5 |
| 2 | Qwen 3.5 Omni Plus | 57.2 |
| 3 | Gemini 3 Flash | 51.7 |
| 4 | Qwen3.5 Omni Flash | 33.9 |
| 5 | Gemini 2.5 Pro | 30.8 |
| 6 | Gemini 2.5 Flash Lite | 8.6 |
Interactive version: theaggregate.ai/benchmark?slug=omnigaia · How It Works · Data refreshed daily, snapshot 2026-09-05.