# GLM-5.2 GLM-5.2 is an AI model released by Z.ai on Jun 16 2026. It has 744B parameters, a 1M context window and open weight. Tracked results include 31% on BullshitBench v2, 91.2% on GPQA Diamond and 54.7% on Humanity's Last Exam (with tools). ## Facts | Field | Value | | --- | --- | | Model | GLM-5.2 | | Developer | Z.ai | | Release date | Tuesday, Jun 16 2026 | | Licensing | Open Weight | | Parameters | 744B | | Context window | 1M | ## API pricing All rates in USD per 1,000,000 tokens, pay-as-you-go. | Tier | Input | Cached input | Output | | --- | --- | --- | --- | | Standard | $1.40 | $0.26 | $4.40 | Verified October 19, 2026 against the first-party source: https://docs.z.ai/guides/overview/pricing ## Tracked benchmark scores | Benchmark | Score | Source | What it measures | | --- | --- | --- | --- | | BullshitBench v2 | 31% | [BullshitBench](https://github.com/petergpt/bullshit-benchmark) | Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | | ProgramBench | 0% | [ProgramBench](https://programbench.com/), retrieved 2026-09-11 | The AI receives a working program and its documentation, then builds a replacement from scratch without the original source code, internet access or decompilation. The score is the percentage of 200 programs that pass every behavioral test. We record each model's best published mini-SWE-agent result, including higher reasoning efforts where available. Partial test-pass rates and almost-solved programs do not count toward this score. Equal scores share a rank here; the official board also uses partial progress to break ties. Higher is better. | | SWE-Bench Pro | 62.1% | Lab | Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | | DeepSWE 1.1 | 44% | Lab | Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | | Next.js Evals | 81% | [Next.js Evals](https://nextjs.org/evals) | Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | | Frontier-Bench v0.1 | 5.1% | Lab | A hard, ever-evolving set of real computer tasks — coding, system administration, data work, and more — that an AI agent has to complete on its own. Run by the Harbor / Laude Institute team as the successor to Terminal-Bench (v0.1 is the first release of the task set). The score is the share of tasks solved. Higher is better. | | Terminal-Bench 2.1 | 81% | Lab | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | | Humanity's Last Exam (no tools) | 40.5% | Lab | Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | | Humanity's Last Exam (with tools) | 54.7% | [BenchLM](https://benchlm.ai), retrieved 2026-07-11 | Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | | GPQA Diamond | 91.2% | Lab | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | | GDPval-AA v2 | 1514 | Lab | economically valuable knowledge work (v2, re-based Elo) | ## About GLM-5.2 GLM-5.2 was introduced in June 2026 as Z.ai's update for long-horizon work, extending the model line to a one-million-token context. The release emphasized maintaining progress through lengthy tasks and offering multiple reasoning-effort levels to balance latency and capability. Coding remained a central use case, alongside work that required retaining large amounts of source material. Its attention changes included IndexShare, which reused an indexer across groups of sparse attention layers to reduce computation at long context. Z.ai also improved speculative decoding and released the weights under the MIT License. These details explain the release's direction: longer inputs needed architectural and serving improvements as well as training for more persistent agent behavior. ## Questions and answers ### When was GLM-5.2 released? GLM-5.2 was released by Z.ai on Tuesday, Jun 16 2026. ### Who made GLM-5.2? GLM-5.2 was built by Z.ai. Chinese AI lab spun out of Tsinghua University (formerly Zhipu AI), building the open-weight GLM family. Rebranded internationally as Z.ai in 2025. ### How much does GLM-5.2 cost? GLM-5.2 costs $1.40 per million input tokens and $4.40 per million output tokens through the Z.ai API. Cached input is $0.26 per million tokens. Rates are pay-as-you-go API prices verified against Z.ai's published pricing on October 19, 2026. ### What benchmark scores did GLM-5.2 get? GLM-5.2 reports 11 tracked benchmark scores — BullshitBench v2: 31%; ProgramBench: 0%; SWE-Bench Pro: 62.1%; DeepSWE 1.1: 44%; Next.js Evals: 81%; Frontier-Bench v0.1: 5.1%; Terminal-Bench 2.1: 81%; Humanity's Last Exam (no tools): 40.5%; Humanity's Last Exam (with tools): 54.7%; GPQA Diamond: 91.2%; GDPval-AA v2: 1514. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data. ### What is the context window of GLM-5.2? GLM-5.2 has a context window of 1M. Providers may specify separate input and output token limits. ### How many parameters does GLM-5.2 have? GLM-5.2 is reported at 744B parameters. ### Is GLM-5.2 open source? Partly. GLM-5.2 is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense. ### What came before and after GLM-5.2? Z.ai's previous tracked release was GLM-5.1 on Apr 7 2026, 70 days earlier. It was followed by GLM-5.3 on Aug 14 2026. --- Canonical page: https://aireleasetracker.com/model/zai/glm-5.2 Site index: https://aireleasetracker.com/llms.txt Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.