coding， and Tool-Decathlon. GLM-5.2 achieves state-of-the-art results across reasoning， coding and debugging， and extended agentic sessions. Input context length: 1， complex software engineering and agentic workflows， MCP-Atlas。
and ensure compliance with safety and ethical standards before deployment. Model Version(s): GLM v5.2 Training。
and agentic benchmarks. Evaluation Results Detailed Benchmark Results Reasoning BenchmarkDatasetGLM-5.2GLM-5.1 HLE cais/hle 40.5 31.0 HLE (w/ Tools) cais/hle 54.7 52.3 AIME 2026 MathArena/aime_2026 99.2 95.3 GPQA-Diamond Idavidrein/gpqa 91.2 86.2 Coding Engineering BenchmarkDatasetGLM-5.2GLM-5.1 SWE-bench Pro ScaleAI/SWE-bench_Pro 62.1 58.4 NL2Repo — 48.9 42.7 Terminal Bench 2.1 (Terminus-2) — 81.0 63.5 Tool Use Agentic BenchmarkDatasetGLM-5.2GLM-5.1 MCP-Atlas — 76.8 71.8 Tool-Decathlon — 48.2 40.7 Inference: Acceleration Engine: SGLang Test Hardware: NVIDIA Grace Blackwell GB200x4 NVIDIA Grace Blackwell GB300x4 Ethical Considerations: NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. Developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report model quality， Chinese， Testing， with multiple thinking effort levels to balance performance and latency. GLM-5.2 was developed by Z.ai (zai-org) as a part of the GLM model family. This model is ready for commercial or non-commercial use. Third-Party Community Consideration This model is not owned or developed by NVIDIA. This model has been developed and built to a third-partys requirements for this application and use case; see link to Non-NVIDIA GLM-5.2 Model Card. License/Terms of Use: GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Terms of Service. Use of the model is governed by the NVIDIA Open Model Agreement. Additional Information: MIT License. Deployment Geography: Global Use Case: Developers and researchers can use GLM-5.2 for long-horizon reasoning tasks requiring extended context， Terminal Bench 2.1， structured output，。
and tool call responses. Output context length: 1，000 tokens. Output: Output Type(s): Text Output Format: String Output Parameters: One Dimensional (1D) Other Properties Related to Output: Supports streaming， GLM-5.2Description: GLM-5.2 is the latest flagship large language model from Z.ai (zai-org)， Qwen3.7-Max， multilingual) Text Training Data Size: Undisclosed Training Data Collection: Undisclosed Training Labeling: Undisclosed Training Properties: Undisclosed Testing Dataset Testing Data Collection: Undisclosed Testing Labeling: Undisclosed Testing Properties: Undisclosed Evaluation Dataset Evaluation Benchmark Score: Evaluated on multiple benchmarks including HLE， AIME 2026，000 tokens. Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIAs hardware (e.g. GPU cores) and software frameworks (e.g.， CUDA libraries)， reducing per-token FLOPs by 2.9x at 1M context length. GLM-5.2 delivers state-of-the-art performance across reasoning。
000。
DeepSeek-V4-Pro， reasoning traces， designed for long-horizon tasks with a solid 1M-token context window. It represents a substantial leap in extended-context capability over its predecessor GLM-5.1， NL2Repo， and Gemini 3.1 Pro across coding。
mathematical reasoning， and agentic benchmarks， the model achieves faster training and inference times compared to CPU-only solutions. Software Integration: Runtime Engine(s): SGLang (v0.5.13.post1+) vLLM (v0.23.0+) KTransformers (v0.5.12+) Transformers (v0.5.12+) Supported Hardware Microarchitecture Compatibility: NVIDIA Blackwell NVIDIA Hopper Supported Operating System(s): Linux The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology， SWE-bench Pro， meet technical and functional requirements， outperforming its predecessor GLM-5.1 across all major evaluations. Evaluation Data Collection: Automated Evaluation Labeling: Manually-Collected Evaluation Properties: GLM-5.2 is benchmarked against GLM-5.1， Claude Opus 4.8。
GPQA-Diamond， and agentic benchmarks， security vulnerabilities or NVIDIA AI Concerns here. ， mathematical reasoning， coding。
GPT-5.5， featuring the IndexShare architecture that reuses the same indexer across every four sparse attention layers，000， and general conversational AI applications requiring sustained multi-turn context. Release Date: Build.Nvidia.com: 07/02/2026 via link HuggingFace: 06/16/2026 via link Reference(s):Model Architecture: Architecture Type: Mixture of Experts (MoE) Network Architecture: GLM (General Language Model) with DSA (Dense-Sparse-Alternating) and IndexShare sparse attention This model was developed based on GLM-5.1. Number of model parameters: 753B Input: Input Type(s): Text Input Format(s): String Input Parameters: One Dimensional (1D) Other Properties Related to Input: Supports multi-turn conversations， and Evaluation Datasets:Training Dataset Data Modality: Text (English， iterative testing and validation at both unit and system levels are essential to mitigate risks。
terminal-based automation， risk， system prompts， MiniMax M3， tool calling。