LLM Reference

GLM-5.1

Released
2026-04-07
Last refreshed
2026-06-30
Status
Researched 13d ago
Open sourceCommercial use: permittedCodingRAGAgentsLong contextClassificationJSON / Tool use

GLM-5.1 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 200k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
GLM-5
Released
2026-04-07
Context
200k
Max output
131,072
Parameters
754B total, 40B active
Architecture
Mixture of Experts
Knowledge cutoff
2025-11
Specialization
general
Openness
Open source
License
MITOSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by

Chinese AI research lab developing GLM language models.

Beijing, China
Founded 2019
Website
Pricing
Output / 1M
$3.50
Input / 1M
$1.05

Cheapest of 5 routes · OpenRouter

About

Post-training variant of GLM-5 from Z.ai (Zhipu AI) with enhanced agentic coding capabilities. Released April 7, 2026. 754B parameters (40B active) in Mixture of Experts architecture, 200K token context, 128K max output. Supports autonomous plan–execute–test–fix–optimize loops for up to 8 hours without human intervention. Trained entirely on Huawei Ascend hardware (no Nvidia). Key benchmarks: SWE-bench Pro 58.4 (world #1 at release, surpassing GPT-5.4 57.7 and Claude Opus 4.6 57.3), GPQA Diamond 86.2, AIME 2026 95.3, Terminal-Bench 2.0 63.5, MCP-Atlas 71.8, Chatbot Arena Elo 1475 (June 16, 2026, arena.ai). Available via Z.ai API ($1.40/$4.40 per 1M input/output tokens) and open weights on Hugging Face under MIT license.

GLM-5.1 is an open-source model in the GLM-5 family. The structured metadata tracks a 200k-token context window, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through Z.ai, OpenRouter, Fireworks AI, and 2 more, with the cheapest tracked route listed at $1.05 input and $3.5 output per 1M tokens. Headline tracked benchmarks include SWE-bench Pro 58.4, Google-Proof Q&A 86.2, and Chatbot Arena 1475.0.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ D

1 relevant benchmark in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 5

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
OpenRouter$1.05$3.50-
Serverless
Novita AI$1.38$4.40-
Serverless
Fireworks AI$1.40$4.40-
Serverless
Vercel AI Gateway$1.40$4.40read $0.260
Serverless

Available via routers & gateways(1)

Capabilities

ReasoningFunction CallingTool UseStructured OutputsCode Execution

Benchmark peer barsfor Coding

Benchmark scores(9)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
SWE-bench Pro58.4https://labs.scale.com/leaderboard/swe_bench_pro_public
Google-Proof Q&A86.2diamondhttps://huggingface.co/zai-org/GLM-5.1
Chatbot Arena1475.0text (June 2026)https://arena.ai/leaderboard/text
Terminal-Bench 2.063.5https://huggingface.co/zai-org/GLM-5.1
MCP-Atlas71.8independent evaluation (BenchLM, June 2026)https://benchlm.ai/benchmarks/mcpAtlas
SWE-rebench62.7pass@1 (best of 5 runs)https://swe-rebench.com/leaderboard
AIME 202595.3AIME 2026 (accuracy)https://lushbinary.com/blog/glm-5-1-benchmarks-breakdown-swe-bench-pro-nl2repo-cybergym/
Humanity's Last Exam31.0HLE text-only (accuracy)https://lushbinary.com/blog/glm-5-1-benchmarks-breakdown-swe-bench-pro-nl2repo-cybergym/
GeneBench-Pro1.2xhighhttps://cdn.openai.com/pdf/21938268-21af-442f-af93-3b2249afb241/genebench-pro.pdf

Migration checks

No linked migration route is available for this model yet.

Compare GLM-5.1 with other models

Show all 56 popular comparisonssorted by 7-day search impressions
GLM-5.1 vs Gemini 2.5 Flash297GLM-5.1 vs Grok-3284GLM-5.1 vs Qwen3.6-35B-A3B283GLM-5.1 vs Claude Sonnet 4.5261GLM-5.1 vs Grok 4.3259GLM-5.1 vs Claude Opus 4.5226GLM-5.1 vs Gemini 2.5 Pro212GLM-5.1 vs DeepSeek V3.1148GLM-5.1 vs GPT-5.2 Codex141GLM-5.1 vs Qwen3.6-27B138GLM-5.1 vs GPT-5.2114GLM-5.1 vs Qwen2.5-72B108GLM-5.1 vs Qwen3.5-397B-A17B108GLM-5.1 vs Xiaomi MiMo-V2.5-TTS-Series90GLM-5.1 vs Claude 3.7 Sonnet80GLM-5.1 vs Qwen3.5-35B-A3B69GLM-5.1 vs GPT-5.4-Cyber64GLM-5.1 vs Qwen3.5-27B63GLM-5.1 vs DeepSeek R1 Lite59GLM-5.1 vs Trinity-Large-Thinking58GLM-5.1 vs Llama 3 8B Instruct55GLM-5.1 vs Together AI Qwen2-7B-Instruct54GLM-5.1 vs Grok Build 0.153GLM-5.1 vs o351GLM-5.1 vs Qwen2.5-72B-Instruct50GLM-5.1 vs Gemini 2.5 Pro Preview 05-0648GLM-5.1 vs Mistral Large 246GLM-5.1 vs Phi-3 Mini 4k44GLM-5.1 vs Qwen3-Max43GLM-5.1 vs Llama 3 70B Instruct40GLM-5.1 vs Llama 3.1 70B Instruct40GLM-5.1 vs DeepSeek R1 052834GLM-5.1 vs Mistral Nemotron29GLM-5.1 vs Qwen3.5-122B-A10B27GLM-5.1 vs Llama Guard 3 1B26GLM-5.1 vs Phi-4 Mini Flash Reasoning24GLM-5.1 vs Qwen3.6 Max Preview24GLM-5.1 vs Gemma 7B Instruct23GLM-5.1 vs Llama 2 13B Chat21GLM-5.1 vs Llama 3.2 1B Instruct21GLM-5.1 vs o3 Mini17GLM-5.1 vs DeepSeek V3.217GLM-5.1 vs ShieldGemma 9B15GLM-5.1 vs Mixtral 8x7B14GLM-5.1 vs o3 Deep Research14GLM-5.1 vs GPT-5.3-Codex14GLM-5.1 vs Claude Haiku 4.512GLM-5.1 vs Qwen3-235B-A22B9GLM-5.1 vs Llama 3.1 405B Instruct6GLM-5.1 vs Grok 3 Mini5GLM-5.1 vs Code Cushman 0024GLM-5.1 vs Gemma 2 9B SahabatAI Instruct4GLM-5.1 vs GPT-5.5 Instant4GLM-5.1 vs Together AI - Llama 3 8B Lite3GLM-5.1 vs Gemini 2.5 Flash Live API2GLM-5.1 vs Qwen2-7B-Instruct2

Frequently asked questions

What is the context window of GLM-5.1?

GLM-5.1 has a context window of 200k tokens.

What is the max output of GLM-5.1?

GLM-5.1 can generate up to 131,072 output tokens.

How much does GLM-5.1 cost?

GLM-5.1 pricing ranges from $1.05/1M to $1.4/1M input tokens depending on the provider.

When was GLM-5.1 released?

GLM-5.1 was released on 2026-04-07.

Which providers offer GLM-5.1?

GLM-5.1 is available from 5 providers: Z.ai, OpenRouter, Fireworks AI, Vercel AI Gateway, Novita AI.

What benchmarks has GLM-5.1 been tested on?

GLM-5.1 has been evaluated on 9 benchmarks, including SWE-bench Pro, Google-Proof Q&A, Chatbot Arena, Terminal-Bench 2.0, MCP-Atlas.