BestHub
Sign in
Kuaishou Large Model
Kuaishou Large Model
Aug 19, 2025 · Artificial Intelligence

How Klear-Reasoner Achieves SOTA Math & Code Reasoning with GPPO

Klear-Reasoner, built on Qwen3‑8B‑Base, introduces the Gradient‑Preserving Clipping Policy Optimization (GPPO) algorithm to overcome traditional clip limitations, achieving state‑of‑the‑art performance on AIME2024/2025 and LiveCodeBench while providing detailed experimental analysis and data‑quality insights.

GPPOcode reasoninggradient clipping
0 likes · 11 min read
How Klear-Reasoner Achieves SOTA Math & Code Reasoning with GPPO
Kuaishou Tech
Kuaishou Tech
Aug 18, 2025 · Artificial Intelligence

How Klear-Reasoner Achieves SOTA Math & Code Reasoning with GPPO Optimization

The Klear‑Reasoner model, built on Qwen3‑8B‑Base and powered by the novel Gradient‑Preserving Clipping Policy Optimization (GPPO) algorithm, surpasses same‑size open‑source baselines on challenging math (AIME) and code (LiveCodeBench) benchmarks, while revealing key insights on data quality, reward design, and clipping strategies for large‑language‑model reasoning.

GPPOLLMcode reasoning
0 likes · 11 min read
How Klear-Reasoner Achieves SOTA Math & Code Reasoning with GPPO Optimization