Gate News reports that on March 25, SWE-rebench benchmark maintainer Ibragim announced the latest leaderboard update on March 23. SWE-rebench is a real-time benchmark that extracts new software engineering tasks from GitHub every month, and the models cannot be optimized in advance for the tasks. This update removes the previous demonstration examples and 80-step operation limit, and adds auxiliary evaluation tasks.
The top ten rankings are: 1. Claude Opus 4.6 (65.3%); 2. GPT-5.2 medium (64.4%); 3. GLM-5 (62.8%); 4. GPT-5.4 medium (62.8%); 5. Gemini 3.1 Pro Preview (62.3%); 6. DeepSeek-V3.2 (60.9%); 7. Claude Sonnet 4.6 (60.7%); 8. Claude Sonnet 4.5 (60.0%); 9. Qwen3.5-397B-A17B (59.9%); 10. Step-3.5-Flash (59.6%).
The open-source model GLM-5 (MIT License) from Zhipu AI ranks third with 62.8%, making it the highest-ranked open-source model on the list. Four Chinese models are in the top ten, besides GLM-5, including DeepSeek-V3.2 (6th), Alibaba’s Tongyi Qianwen Qwen3.5-397B-A17B (9th), and Step-3.5-Flash (10th). Zhipu AI’s global head Li Zixuan stated that during the last SWE-rebench update, all Chinese models were outside the top ten.
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to
Disclaimer.
