Orion-14B-Base
Orion-14B-Base is an AI model published by OrionStar, released on 2024-01-22, for Foundation model, with 14B parameters, and 200K context length, requiring about 28GB storage, with a 72.90 score on C-Eval.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Model basics
Open source & experience
Official resources
API details
Benchmark Results
Orion-14B-Base currently shows benchmark results led by AGIEval (5 / 28, score 54.70), C-Eval (17 / 48, score 72.90), MMLU (75 / 124, score 69.90). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
Publisher
Model Overview
Orion-14B-Base is an AI model published by OrionStar, released on 2024-01-22, for Foundation model, with 14B parameters, and 200K context length, requiring about 28GB storage, with a 72.90 score on C-Eval.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
