GLM 5
Z.ai (Zhipu AI)huggingface.co/zai-org/GLM-5
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...
Updated 13 min ago · first seen 11 Sept 2026
model_01M294WW58QZ2KAA2XSGNFKSQ5
- Parameters
- 753.9B
- T2 · 5 h ago
- Context
- 204.8K tokens
- T2 · 2 h ago
- Released
- 11 Feb 2026
- T2 · 5 h ago
- License
- mit
- T2 · 4 h ago
Specification
- Release date
- 11 Feb 2026
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Status
- deprecated
Source:Artificial AnalysisT2observed 4 h agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- License
- mit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Architecture
- GlmMoeDsaForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Parameters
- 753.9B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Context window
- 204.8K tokens
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Max output
- 128K tokens
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Modalities
- text
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Input modalities
- text
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Languages
- en, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- File size
- 1507.7 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Hugging Face repo
- zai-org/GLM-5
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Downloads
- 60,650
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 min agomedium
- Likes
- 2,119
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Hf inference providers
- deepinfra, featherless-ai, novita, zai-org
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Last modified
- 2026-08-11T07:36:34+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Aa median output tokens per second
- 65.4
Source:Artificial AnalysisT2observed 4 h agomedium
- Downloads all time
- 1,341,187
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 min agomedium
- Model type
- glm_moe_dsa
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Openrouter id
- z-ai/glm-5
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Supported parameters
- frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Tags
- transformers, safetensors, glm_moe_dsa, text-generation, en, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Weights dtype
- BF16, F32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
33
Source tiers
T233
Freshest observation
13 min ago
Conflicts
None
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 204.8K tokens
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Max output
- 128K tokens
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Languages
- en, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| τ²-bench | 98.25% | pass^1 | aa_slug=glm-5 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Artificial Analysis Intelligence Index | 27.91 | index | aa_slug=glm-5 · version=4.3 · estimated=true | — | artificialanalysis.aiT2 |
| GPQA | 82.02% | accuracy | aa_slug=glm-5 · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 29.29% | accuracy | aa_slug=glm-5 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| IFBench | 72.31% | accuracy | aa_slug=glm-5 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| SWE-bench Multilingual | 69.7% | resolved | date=2026-02-13 · board=Multilingual · system=mini-SWE-agent · model_tag=glm-5 | 13 Feb 2026 | swebench.comT2 |
| SWE-bench Verified | 72.8% | resolved | date=2026-02-17 · board=Verified · system=mini-SWE-agent · model_tag=glm-5 | 17 Feb 2026 | swebench.comT2 |
| Terminal-Bench | 43.18% | accuracy | aa_slug=glm-5 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| Z.ai APIz-ai/glm-5 | $0.60 | $1.92 | $0.12 | — | 198K | 1 h ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- Z.ai API
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| NVIDIA DGX B200 | 4bit | 1,440 GB | 434.0 GB | Yes |
| Apple M3 Ultra | 4bit | — | 434.0 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 434.0 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 434.0 GB | No |
| AMD Instinct MI300X | 4bit | 192 GB | 434.0 GB | No |
| Apple M2 Ultra | 4bit | — | 434.0 GB | No |
| NVIDIA B200 | 4bit | 180 GB | 434.0 GB | No |
| NVIDIA H200 | 4bit | 141 GB | 434.0 GB | No |
| NVIDIA H200 NVL | 4bit | 141 GB | 434.0 GB | No |
| Apple M1 Ultra | 4bit | — | 434.0 GB | No |
| Apple M3 Max | 4bit | — | 434.0 GB | No |
| Apple M4 Max | 4bit | — | 434.0 GB | No |
| Mac Studio (Apple M5 Max) | 4bit | — | 434.0 GB | No |
| MacBook Pro (Apple M5 Max) | 4bit | — | 434.0 GB | No |
| NVIDIA DGX Spark | 4bit | 128 GB | 434.0 GB | No |
| Apple M2 Max | 4bit | — | 434.0 GB | No |
| NVIDIA H100 NVL | 4bit | 94 GB | 434.0 GB | No |
| NVIDIA A100 80GB | 4bit | 80 GB | 434.0 GB | No |
| NVIDIA H100 SXM | 4bit | 80 GB | 434.0 GB | No |
| Apple M1 Max | 4bit | — | 434.0 GB | No |
| Apple M4 Pro | 4bit | — | 434.0 GB | No |
| Mac mini (Apple M5 Pro) | 4bit | — | 434.0 GB | No |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 434.0 GB | No |
| Apple M3 Pro | 4bit | — | 434.0 GB | No |
| Apple M1 Pro | 4bit | — | 434.0 GB | No |
| Apple M2 Pro | 4bit | — | 434.0 GB | No |
| Apple M4 | 4bit | — | 434.0 GB | No |
| iMac (Apple M4) | 4bit | — | 434.0 GB | No |
| Mac mini (Apple M6) | 4bit | — | 434.0 GB | No |
| MacBook Air (Apple M5) | 4bit | — | 434.0 GB | No |
| MacBook Pro (Apple M5) | 4bit | — | 434.0 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 434.0 GB | No |
| Apple M2 | 4bit | — | 434.0 GB | No |
| Apple M3 | 4bit | — | 434.0 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 434.0 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 434.0 GB | No |
| Apple M1 | 4bit | — | 434.0 GB | No |
No lineage recorded
Papers 1
- arXiv:2602.15763Active35
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Hf inference providers
Hf inference providershf_inference_providers1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| deepinfra, featherless-ai, novita, zai-org | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
GLM 5: context length changed from 200000 to 204800
Context window200K tokens→204.8K tokensopenrouterGLM 5 scores 72.8% on SWE-bench Verified
swebench_leaderboardGLM 5 scores 69.7% on SWE-bench Multilingual
swebench_leaderboardGLM 5 scores 29.29% on Humanity's Last Exam
artificial_analysisGLM 5 scores 27.91 on Artificial Analysis Intelligence Index
artificial_analysisGLM 5: context length changed from 204800 to 200000
Context window204.8K tokens→200K tokensartificial_analysisZ.ai API lists GLM 5 at $0.6 in / $1.92 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/zai-org/GLM-5 | model_page | T2· Quality secondary | 13 min ago | 4 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=zai-org&p=0&sort=downloads | listing | T2· Quality secondary | 52 min ago | 4 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 1 h ago | 4 |
| SWE-bench leaderboards | swebench.com/ | leaderboard | T2· Quality secondary | 4 h ago | 1 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 4 h ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/zai-org/GLM-5/raw/main/README.md | model_card | T2· Quality secondary | 4 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.