Qwen-3 8B

The 'Qwen-3 8B' is a benchmark used to evaluate the performance of large language models in multi-turn code generation tasks, specifically measuring their ability to achieve high Pass@1 scores on the LiveCodeBench dataset.

Papers using Qwen-3 8B (3)

Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)2026Step-wise Rubric Rewards for LLM Reasoning2026Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation2026