Z.ai

GLM 5

Tool callingStructured outputReasoning
GLM 5 model card cover

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

Context
205K
Released
8mo ago
Parameters
—
Input / 1M tokens
$1.00
Output / 1M tokens
$3.20
Cached input / 1M tokens
$0.20

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Other published benchmarks

EvaluationReported score and source
ARC-AGI-2
4.9%
Third-party evaluator · glm-5
External evaluation via Epoch AI
Original-source terms apply
FrontierMath-2025-02-28-Private
16.4%
Epoch AI · glm-5
Epoch AI evaluation
FrontierMath-Tier-4-2025-07-01-Private
2.1%
Epoch AI · glm-5
Epoch AI evaluation
GPQA diamond
87.8%
Epoch AI · glm-5
Epoch AI evaluation
OTIS Mock AIME 2024-2025
80.0%
Epoch AI · glm-5
Epoch AI evaluation
SWE-Bench verified
72.1%
Epoch AI · glm-5
Epoch AI evaluation
Terminal Bench
52.4%
https://www.tbench.ai/leaderboard/terminal-bench/2.0 · glm-5
Agent: Terminus 2
https://www.tbench.ai/leaderboard/terminal-bench/2.0
Original-source terms apply

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Specifications

Developer
Z.ai
Model family
GLM
Type
Language model
Predecessor
—
Successor
—
Released
February 12, 2026
Model ID
z-ai/glm-5
Openness
Open weights
License
—
Parameters
—
Input modalities
text
Output modalities
text
Modality
text->text
Tokenizer
Other
Max output tokens
131K
Hugging Face
zai-org/GLM-5
Source freshness
Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
Source model
zhipuai/glm-5
Source family
glm
Last updated
2026-02-12
Model context
205K
Model output limit
131K
Open weights
Yes
File attachments
No
Reasoning
Yes
Tool calling
Yes
Temperature control
Yes

Downloadable weights

Published benchmarks

BenchmarkScoreEvaluation detailsEvidence
SWE-Bench Verified72.8 · resolved—Source
SWE-Atlas Codebase QnA20.5 · scoreMini-SWE-AgentSource
SWE-Atlas Refactoring24.24 · scoreMini-SWE-AgentSource
SWE-Atlas Test Writing28.74 · scoreMini-SWE-AgentSource
Complete source record (JSON)
{
  "id": "zhipuai/glm-5",
  "name": "GLM-5",
  "description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
  "family": "glm",
  "last_updated": "2026-02-12",
  "attachment": false,
  "reasoning": true,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 204800,
    "output": 131072
  },
  "benchmarks": [
    {
      "name": "SWE-Bench Verified",
      "score": 72.8,
      "source": "https://www.swebench.com/",
      "metric": "resolved"
    },
    {
      "name": "SWE-Atlas Codebase QnA",
      "score": 20.5,
      "source": "https://labs.scale.com/leaderboard/sweatlas-qna",
      "metric": "score",
      "harness": "Mini-SWE-Agent"
    },
    {
      "name": "SWE-Atlas Refactoring",
      "score": 24.24,
      "source": "https://labs.scale.com/leaderboard/sweatlas-refactoring",
      "metric": "score",
      "harness": "Mini-SWE-Agent"
    },
    {
      "name": "SWE-Atlas Test Writing",
      "score": 28.74,
      "source": "https://labs.scale.com/leaderboard/sweatlas-tw",
      "metric": "score",
      "harness": "Mini-SWE-Agent"
    }
  ],
  "release_date": "2026-02-12",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/zai-org/GLM-5"
    }
  ]
}

Infrastructure

Provider availability

All providers
ProviderEndpointContextInput /M tokensOutput /M tokensCached input /M tokensCache write /M tokensUptime 1dData handling
GMICloudgmicloud/fp8203K$0.60$1.92$0.12—99.72%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

StreamLakestreamlake/fp8198K$0.60$1.92$0.12—100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Baidubaidu/fp8203K$0.70$2.24$0.14—100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

SiliconFlowsiliconflow/fp8205K$0.95$2.55$0.20—99.78%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Amazon Bedrockamazon-bedrock203K$1.00$3.20——96.88%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Novitanovita/fp8203K$1.00$3.20$0.20—100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Venicevenice/fp8198K$1.00$3.20$0.20—85.71%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Z.AIz-ai/fp8203K$1.00$3.20$0.20—100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware