Chinese AI firm Z.ai has launched GLM-5.1, an open-source coding mannequin it says is constructed for agentic software program engineering. The launch comes as AI distributors transfer past autocomplete-style coding instruments towards methods that may deal with software program duties over longer durations with much less human enter.
Z.ai stated GLM-5.1 can maintain efficiency over lots of of iterations, a capability it argues units it other than fashions that lose effectiveness in longer classes.
As one instance, the corporate stated GLM-5.1 improved a vector database optimization activity over greater than 600 iterations and 6,000 device calls, reaching 21,500 queries per second, about six occasions the most effective outcome achieved in a single 50-turn session.
In a analysis observe, Z.ai stated GLM-5.1 outperformed its predecessor, GLM-5, on a number of software program engineering benchmarks and confirmed explicit energy in repo technology, terminal-based downside fixing, and repeated code optimization. The firm stated the mannequin scored 58.Four on SWE-Bench Pro, in contrast with 55.1 for GLM-5, and above the scores it listed for OpenAI’s GPT-5.4, Anthropic’s Opus 4.6, and Google’s Gemini 3.1 Pro on that benchmark.
GLM-5.1 has been launched underneath the MIT License and is on the market by means of its developer platforms, with mannequin weights additionally printed for native deployment, the corporate stated. That might enchantment to enterprises searching for extra management over how such instruments are deployed.
Longer-running coding brokers
Z.ai says long-running efficiency is a key differentiator for the corporate when in comparison with fashions that lose effectiveness in prolonged classes.
Analysts say it is because many present fashions nonetheless plateau or drift after a comparatively small variety of turns, limiting their usefulness on prolonged, multi-step software program duties.
Pareekh Jain, CEO of Pareekh Consulting, stated the trade is now transferring past instruments that may reply prompts towards methods that may perform longer assignments with much less supervision.
The query, Jain stated, is now not, “What can I ask this AI?” however, “What can I assign to it for the next eight hours?”
For enterprises, that raises the prospect of assigning an agent a ticket within the morning and receiving an optimized resolution by day’s finish, after it has run lots of of experiments and profiled the code.
“This capability aligns with real needs such as large refactors, migration programs, and continuous incident resolution,” stated Charlie Dai, VP and principal…
