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

#ModelScore
1Gemini 3 Pro62.5
2Qwen 3.5 Omni Plus57.2
3Gemini 3 Flash51.7
4Qwen3.5 Omni Flash33.9
5Gemini 2.5 Pro30.8
6Gemini 2.5 Flash Lite8.6

Interactive version: theaggregate.ai/benchmark?slug=omnigaia · How It Works · Data refreshed daily, snapshot 2026-09-05.