Understand this story
Developer ActbroDev built the System 1 decision model MiniCPM5-2B-Jev based on OpenBMB's MiniCPM5-2B; after inputting a document and a question, it directly returns the probabilities of predefined options rather than generating free text. The project report states that the model scores 78.79% on JevBench, ranking first among open-weight System 1 / Jev models with ≤2B parameters, with 86.41% accuracy on the decision-v7 benchmark and an ECE of 0.0307. The code, LoRA adapter, and calibration head are open-sourced under Apache 2.0, and a /v1/systemone structured decision API and shared-context KV-cache reuse are provided.
AI-generated from public reports
Latest development · Report
MiniCPM5-2B-Jev Decision Model Released: 78.79% on JevBenchDevelopments
1 confirmed developments
- Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 28
ModelBest OpenBMB
MiniCPM5-2B-Jev Decision Model Released: 78.79% on JevBench
Developer ActbroDev built the System 1 decision model MiniCPM5-2B-Jev based on OpenBMB's MiniCPM5-2B. After inputting a document and a question, it directly returns the probabilities of predefined options rather than generating free text. The project reports that it scores 78.79% on JevBench, ranking first among ≤2B open-weight System 1 / Jev models, with 86.41% accuracy on the decision-v7 benchmark and an ECE of 0.0307. The code, LoRA adapters, and calibration head are open-sourced under Apache 2.0, and it provides a /v1/systemone structured decision API and shared-context KV-cache reuse.