Comprehensively upgraded multimodal capabilities, achieving world-class levels in various visual understanding tasks. Its performance in visual reasoning, perception, spatial reasoning, and long-context understanding is particularly outstanding. Doubao 2.0 Pro has achieved the highest scores in most related benchmark tests. In reasoning and Agent capability assessments, Doubao 2.0 Pro won gold medals in the IMO, CMO Math Olympiad, and ICPC programming competitions. It also surpassed Gemini 3 Pro's performance on the Putnam Bench, demonstrating strong mathematical and reasoning abilities. In HLE-text (Human's Last Exam), Doubao 2.0 Pro scored the highest with 54.2 points and also performed excellently in tool invocation and instruction-following tests.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
Doubao 2.0 Officially Launches
Comprehensively upgraded multimodal capabilities, achieving world-class levels in various visual understanding tasks. Its performance in visual reasoning, perception, spatial reasoning, and long-context understanding is particularly outstanding. Doubao 2.0 Pro has achieved the highest scores in most related benchmark tests.
In reasoning and Agent capability assessments, Doubao 2.0 Pro won gold medals in the IMO, CMO Math Olympiad, and ICPC programming competitions. It also surpassed Gemini 3 Pro's performance on the Putnam Bench, demonstrating strong mathematical and reasoning abilities. In HLE-text (Human's Last Exam), Doubao 2.0 Pro scored the highest with 54.2 points and also performed excellently in tool invocation and instruction-following tests.