Editorial illustration for z.ai's GLM-5 logs record low hallucination rate, beats Moonshot's Kimi K2.5
GLM-5: Open Source AI Slashes Hallucination Rates
z.ai's GLM-5 logs record low hallucination rate, beats Moonshot's Kimi K2.5
Every new AI model claims to beat the last. This one might. Z.ai's open-source GLM-5 just posted a record-low hallucination rate.
It even topped Moonshot's freshly released Kimi K2.5 on key tests. The secret is a new reinforcement learning technique called "slime." Its scores on coding and business simulation benchmarks now nip at the heels of Google's Gemini and Anthropic's Claude. The gap between Western labs and Chinese open-source projects?
A thin line.
High performance GLM-5's benchmarks make it the new most powerful open source model in the world, according to Artificial Analysis, surpassing Chinese rival Moonshot's new Kimi K2.5 released just two weeks ago, showing that Chinese AI companies are nearly caught up with far better resourced proprietary Western rivals. According to z.ai's own materials shared today, GLM-5 ranks near state-of-the-art on several key benchmarks: SWE-bench Verified: GLM-5 achieved a score of 77.8, outperforming Gemini 3 Pro (76.2) and approaching Claude Opus 4.6 (80.9). Vending Bench 2: In a simulation of running a business, GLM-5 ranked #1 among open-source models with a final balance of $4,432.12. Beyond performance, GLM-5 is aggressively undercutting the market.
Price matters. Reliability matters more. Z.ai built GLM-5 for both, using that "slime" method to cut costs and errors.
For developers, that's the game. The race has shifted. It's no longer just about the smartest model.
It's about the most practical one—the one you can afford to run. Chinese firms like z.ai are now writing those rules. The era of clear Western dominance is ending.
Call it a correction.
Related Reading
Open Source D&B rebuilds 642 million‑business database after AI agents hit limits
Open Source OpenAI's GPT Transcribe Cuts Error Rate to 3.31%, Improving on GPT-4o
Open Source Study: 6.7% of Deepfake Requests on Hugging Face Targeted Children
From Archives MiniMax's M2.5 costs 1/20 of Claude Opus, covers 30% of HQ tasks
From Archives Jeffrey Epstein Consulted Elon Musk Ally on Potential Tesla Privatization
Common Questions Answered
What makes GLM-5's hallucination rate significant in the AI industry?
GLM-5 achieved a record-low hallucination rate with a score of -1 on the Artificial Analysis Intelligence Index v4.0, representing a 35-point improvement over previous models. This breakthrough suggests a major advancement in AI reliability and accuracy, potentially addressing one of the most critical challenges in large language model development.
How does GLM-5's architecture differ from its previous generations?
GLM-5 scales up to 744 billion total parameters with 40 billion active parameters, a significant increase from the previous 355 billion total parameters with 32 billion active parameters. The model integrates DeepSeek Sparse Attention and uses a Mixture-of-Experts architecture, expanding its pre-training to 28.5 trillion tokens and improving its overall performance capabilities.
What is unique about GLM-5's development and licensing approach?
GLM-5 is released with an open-source MIT license, allowing for flexible enterprise deployment and avoiding vendor lock-in. The model was uniquely trained entirely on Huawei Ascend chips, emphasizing China's commitment to technological independence in AI infrastructure.
Further Reading
- GLM-5 - Everything you need to know — Artificial Analysis
- GLM-5: From Vibe Coding to Agentic Engineering — Z.ai
- vectara/hallucination-leaderboard — GitHub/Vectara
- Why Kimi K2.5 Beats Gemini on Hallucination Benchmarks — YouTube
