Chinese GLM-5.2 model outperforms GPT-5.5 on coding benchmarks, offers lower cost · 1 source tracked

The Chinese AI model GLM-5.2, developed by Z.ai (formerly Zhipu AI) and released on June 13, 2026, has demonstrated superior performance over OpenAI's GPT-5.5 in specific coding benchmarks, achieving a score of 62.1 on SWE-bench Pro compared to GPT-5.5's 58.6. This open-weight model, available under an MIT license, also offers a significantly lower cost, priced at $5.80 per million tokens, which is approximately one-sixth the cost of GPT-5.5. While GLM-5.2 excels in certain coding and agent tasks, it reportedly underperformed GPT-5.5 on the Terminal-Bench. The model boasts a large context window of up to 1 million tokens and utilizes a Mixture of Experts architecture. AI

IMPACT Sets new SOTA on coding benchmarks, potentially challenging OpenAI's dominance and accelerating adoption of open-weight models.

RANK_REASON Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on dev.to — LLM tag →

• GLM-5.2
• GPT-5.5
• Hugging Face
• MIT
• OpenAI
• SWE-bench Pro
• Terminal-Bench
• Z.ai

• model release
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →