Update README.md

README.md

@@ -1,26 +1,25 @@
 ---
 license: apache-2.0
 language:
-- en
+- multilingual
 base_model:
 - Qwen/Qwen3-4B-Instruct-2507
 pipeline_tag: text-generation
 tags:
-- performance-prediction
-- llm-evaluation
-- meta-learning
+- Model Routing
+- LLM reasoning
 ---
 
-# SCOPE: LLM Performance Prediction Model
+# SCOPE: Scalable and Controllable Outcome Performance Estimator
 
 SCOPE is a specialized model that predicts how a target LLM will perform on a given question. Given a target question and a set of anchor questions with known performance results, SCOPE predicts the **output length** and **correctness** of the target model's response.
 
 ## Model Description
 
 - **Task**: Performance prediction for LLMs
-- **Base Model**: Qwen3-4B
-- **Training**: Supervised Fine-Tuning (SFT) + Reinforcement Learning with Chain-of-Thought reasoning
-- **Input**: Target question + 5 anchor questions with performance data
+- **Base Model**: Qwen/Qwen3-4B-Instruct-2507
+- **Training**: Supervised Fine-Tuning (SFT) + Reinforcement Learning (GRPO)
+- **Input**: Target question + k anchor questions with performance data
 - **Output**: Predicted length (tokens) and correctness (yes/no)
 
 ## Intended Use