See and act, performance surpasses Jev: Shanghai AI Lab launches decision model 'Shusheng Mingjue', achieving dual upgrades in response efficiency and quality — forck
See and act, performance surpasses Jev: Shanghai AI Lab launches decision model 'Shusheng Mingjue', achieving dual upgrades in response efficiency and quality看见即行动、性能超Jev，上海AI实验室推出决策模型“书生·明决”，实现响应效率与质量双升级
New decision model outperforms Jev on benchmarks and latency
New model
Image from shlab.org.cn
Shanghai AI Lab released Intern-Decision (Shusheng Mingjue), a decision-making model that outperforms Jev and other open-source models on seven benchmarks, with three parameter sizes: 0.8B, 2B and 4B.
The model integrates native visual perception with instruction following, enabling it to make decisions directly from visual input without separate image processing.
On a single RTX 4090, the 0.8B and 2B models achieve about 30 decisions per second with roughly 33 ms latency, while the 4B model averages 44.16 ms — more than twice as fast as Jev's 109.70 ms.
AI and science form a dual-wheel drive for new paradigm shifts
The 4B model scored 90.02 average across seven tasks, 1.28 points higher than Jev's 88.74, and topped the leaderboard.
The team also explored a confidence-based routing mechanism where Intern-Decision handles routine judgments and passes uncertain cases to a larger model, cutting total task time by about 53% while losing only two correct answers.
