Model
Gemini-3-Pro
A multimodal large language model in Google's Gemini series, supporting understanding and generation across modalities such as text and images.
Timeline (last 90 days)
Oct 12
On OmniParsingBench Youtu averages 75.08, below Gemini-3-Pro's 77.44; it wins on charts at 95.02 and audio at 78.08, but clearly lags on natural images at 62.84 versus 69.73 and geometry at 74.33 versus 85.43.
Unverified50%
Sep 18
The study evaluated models including Qwen3-Max, Gemini-3-Pro, and DeepSeek-V3.2.
Unverified50%
All Facts (2)
Unverified
On OmniParsingBench Youtu averages 75.08, below Gemini-3-Pro's 77.44; it wins on charts at 95.02 and audio at 78.08, but clearly lags on natural images at 62.84 versus 69.73 and geometry at 74.33 versus 85.43.
50%UnverifiedThe study evaluated models including Qwen3-Max, Gemini-3-Pro, and DeepSeek-V3.2.
50%