# Z.ai GLM-5.2 Beats GPT-5.5 on SWE-bench Pro

> Source: [https://botensten.com/articles/glm-5-2-beats-gpt-5-5-coding](https://botensten.com/articles/glm-5-2-beats-gpt-5-5-coding) (canonical)
> Author: iCharles News — Botensten, https://botensten.com
> Published: 2026-06-17

## TL;DR

Z.ai launched GLM-5.2 on June 13, 2026. The ~753B open-weights model scores 62.1 on SWE-bench Pro, ahead of GPT-5.5's 58.6. It ships with a 1M-token context window, two thinking-effort levels, and API pricing of $1.40 per million input tokens — roughly one-sixth the cost of closed alternatives, according to VentureBeat. Weights are released under an MIT license with no regional restrictions.

## What is Z.ai's GLM-5.2 and when did it launch?

Z.ai launched **GLM-5.2** on June 13, 2026 — a ~753-billion-parameter mixture-of-experts language model and the third major release in the GLM-5 line. It follows GLM-5 (February 11), GLM-5-Turbo (March 15), and GLM-5.1 (April 7), making four flagship-tier releases in roughly four months. GLM-5.2 is the only open-weights model in the current frontier tier. It is available as `zai-org/GLM-5.2` on Hugging Face under an MIT license with no regional restrictions.

## How does GLM-5.2 score on SWE-bench Pro compared to GPT-5.5?

GLM-5.2 scores 62.1 on SWE-bench Pro. GPT-5.5 scores 58.6. GLM-5.1, the previous version, scored 58.4. That means an open-weights model now leads a closed frontier model on a real software-engineering benchmark, [according to VentureBeat](https://venturebeat.com/technology/z-ais-open-weights-glm-5-2-beats-gpt-5-5-on-multiple-long-horizon-coding-benchmarks-for-1-6th-the-cost).

The Terminal-Bench 2.1 result is also notable. GLM-5.2 scores 81.0, up from GLM-5.1's 62.0. That is a roughly 19-point jump in one generation on terminal-style agentic coding. Z.ai also reports GLM-5.2 as the top open-source model on FrontierSWE, PostTrainBench, and SWE-Marathon.

## How does GLM-5.2 perform on agentic tool-use benchmarks?

On MCP-Atlas — a benchmark measuring Model Context Protocol tool orchestration — GLM-5.2 scores 77.0. GPT-5.5 scores 75.3. Claude Opus 4.8 leads at 77.8. GLM-5.2 sits less than one point behind Claude Opus 4.8 and ahead of GPT-5.5.

On Humanity's Last Exam with tools, Z.ai reports GLM-5.2 at 54.7 versus GPT-5.5's 52.2. GLM-5.2 supports OpenAI-compatible function and tool calling, plus an Anthropic-compatible coding endpoint. That lets it drop into agent harnesses built for Claude without changes to the harness itself.

## What is the 1M-token context window and how does it compare to GLM-5.1?

GLM-5.2 ships with a 1,000,000-token context window, labeled `glm-5.2[1m]` in Z.ai's configuration. Each response can return up to 131,072 output tokens. That is roughly a 5x increase over GLM-5.1's ~200,000-token window, [as MarkTechPost reports](https://www.marktechpost.com/2026/06/14/z-ai-launches-glm-5-2-with-a-usable-1m-token-context-two-thinking-effort-levels-and-no-benchmarks-at-launch/).

A 1M-token window means a coding agent can hold an entire mid-sized repository in working memory — source files, tests, configuration, and conversation history — without constant summarization. Z.ai's docs list use cases including whole-repository refactors, long-horizon agent runs, and large-document analysis past 200K tokens.

## What are GLM-5.2's two thinking-effort levels?

GLM-5.2 offers two reasoning modes: **High** and **Max**. Z.ai recommends Max effort for complex, multi-step coding work. In Claude Code, the `/effort` command controls this setting. The `xhigh`, `max`, and `ultracode` options all map to GLM-5.2's Max effort. Developers can also set `reasoning_effort: "max"` and `thinking: {type: "enabled"}` directly in the API, or disable thinking entirely for fast, low-cost responses.

## How much does GLM-5.2 cost per token?

| Pricing metric | GLM-5.2 |
|---|---|
| API input | $1.40 / 1M tokens |
| API output | $4.40 / 1M tokens |
| Cached input | ~$0.26 / 1M tokens |
| Self-host | Yes (MIT license) |

Pricing is via OpenRouter, as cited by VentureBeat. The closed alternatives — GPT-5.5, Claude Opus 4.8, and Gemini 3.1 Pro — are all priced higher, though their exact rates vary by tier and change frequently.

Here's what we know so far: the cost gap is substantial. VentureBeat describes GLM-5.2's pricing as roughly one-sixth the cost of GPT-5.5. For teams running high-volume coding agents, that difference compounds quickly.

## What reasoning and math benchmarks has Z.ai published?

Z.ai reports GLM-5.2 at 99.2 on AIME 2026 and 91.2 on GPQA-Diamond. These are Z.ai's own launch numbers. No independent third-party replication of these scores had been published at the time of launch.

Z.ai also published no SWE-bench, Terminal-Bench, or Code Arena numbers at the initial announcement on June 13. The SWE-bench Pro and Terminal-Bench figures cited in this article come from Z.ai's subsequent head-to-head comparisons, not the launch announcement itself.

## How does GLM-5.2 fit into the broader 2026 frontier model landscape?

The four models drawing the most attention in mid-2026 are GLM-5.2, GPT-5.5, Claude Opus 4.8, and Gemini 3.1 Pro. GLM-5.2 is the only one with open weights. The other three are closed, API-only, and do not allow self-hosting.

| Model | Weights | SWE-bench Pro | MCP-Atlas | Input price |
|---|---|---|---|---|
| GLM-5.2 | Open (MIT) | 62.1 | 77.0 | $1.40/1M |
| GPT-5.5 | Closed | 58.6 | 75.3 | Higher |
| Claude Opus 4.8 | Closed | n/a | 77.8 | Higher |
| Gemini 3.1 Pro | Closed | n/a | n/a | Higher |

Claude Opus 4.8 leads on MCP-Atlas at 77.8. Gemini 3.1 Pro is the closest competitor on long-context document work. GPT-5.5 remains a strong generalist coder with tight integration into the OpenAI tooling ecosystem. None of that changes the SWE-bench Pro result.

Discussions about open-weights models like GLM-5.2 sit alongside broader policy conversations about AI access — the kind of access questions that surfaced when the US government weighed [DeepSeek trade restrictions](/articles/deepseek-entity-list-blacklist-delayed). Open licensing and self-hosting rights are increasingly part of how developers evaluate frontier models, not just benchmark scores.

The GLM-5.2 architecture uses "IndexShare" sparse attention, which reuses one indexer across every four sparse-attention layers. This cuts attention cost at long context — a structural advantage for agents that accumulate large tool-call histories.

For builders tracking how AI labs are positioning at the policy and industry level, the [G7 AI Summit](/articles/altman-amodei-hassabis-g7-summit) brought together leaders from OpenAI, Anthropic, and DeepMind — the companies behind GLM-5.2's closed competitors. And for context on how AI productivity claims translate to real economic outcomes, see our coverage of [AI and the US deficit](/articles/ai-productivity-deficit-yale-budget).

Z.ai confirmed that open weights for GLM-5.2 were pending release the week following the June 13 launch. That is the next confirmed milestone from the sources.

<!--il:v1-->

## Frequently asked questions

****What score did GLM-5.2 get on SWE-bench Pro?****

GLM-5.2 scored 62.1 on SWE-bench Pro, according to Z.ai's published results. That places it ahead of GPT-5.5, which scored 58.6, and GLM-5.1, which scored 58.4. SWE-bench Pro is a software-engineering benchmark. Z.ai also reports GLM-5.2 as the top open-source model on FrontierSWE, PostTrainBench, and SWE-Marathon.

****How large is GLM-5.2's context window?****

GLM-5.2 supports a 1,000,000-token context window, labeled `glm-5.2[1m]` in Z.ai's configuration. Each response can return up to 131,072 output tokens. That is roughly five times larger than GLM-5.1's ~200,000-token window. The larger window allows a coding agent to hold an entire mid-sized repository in working memory without summarization.

****What does GLM-5.2 cost per million tokens?****

GLM-5.2 is priced at $1.40 per million input tokens and $4.40 per million output tokens via OpenRouter, as cited by VentureBeat. Cached input costs approximately $0.26 per million tokens. VentureBeat describes this as roughly one-sixth the cost of GPT-5.5. The model can also be self-hosted under its MIT license, which eliminates API costs entirely.

****Is GLM-5.2 open source?****

Yes. GLM-5.2 is released under an MIT license with no regional restrictions. It is available as `zai-org/GLM-5.2` on Hugging Face. Z.ai confirmed at launch that the open weights were pending release the week following the June 13 announcement. GLM-5.2 is the only open-weights model among the four frontier models compared in mid-2026.

****What are GLM-5.2's two thinking-effort levels?****

GLM-5.2 offers High and Max reasoning modes. Z.ai recommends Max for complex, multi-step coding tasks. In Claude Code, the `/effort` command controls the setting, and the `xhigh`, `max`, and `ultracode` options all map to Max effort. Developers can also configure reasoning directly in the API using `reasoning_effort: "max"` and `thinking: {type: "enabled"}`.