Intelligence
23 scoreZ AI · Flagships Analysis
GLM-4.6
Intelligence, Performance & Price Analysis
Canonical slug: glm-4-6 · Canonical model registry at build time
Speed
43.8 output tokens/secLatency
3.62s TTFTInput Price
$0.57 / 1M tokensOutput Price
$2.20 / 1M tokensExecutive Assessment
Routing Verdict & Tradeoffs
Ethen Routing Verdict
Strong general-purpose model
GLM-4.6 (Non-reasoning) scores 23 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 17). GLM-4.6 (Non-reasoning) generates output at 43.8 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 58.7 t/s). GLM-4.6 (Non-reasoning) costs $0.57 per 1M input tokens (better than average, median: $0.60) and $2.20 per 1M output tokens (better than average, median: $2.40), based on the median across providers serving the model.
Suitable for most production tasks, but high-volume or repetitive work should still be compared against cheaper routes.
Task Fit Assessment
| Workload | Rating | Notes |
|---|---|---|
| Complex reasoning & agentic workflows | optimal | Intelligence score 23 supports capable reasoning, but very hard tasks may benefit from higher-tier models. |
| High-volume chat & customer-facing | viable | Output speed may be a bottleneck for real-time chat at scale. |
| Latency-sensitive applications | viable | TTFT 3.62s — latency may be noticeable in interactive use. |
| Cost-sensitive pipelines | viable | Output pricing at $2.20 is premium. Route high-volume simple tasks to cheaper alternatives. |
Cost Pressure Analysis
Medium
Pricing is moderate — input $0.57, output $2.20. Costs accumulate at volume but are manageable for valuable tasks.
Technical Specifications
Architecture and Limits
| Specification | Value | Validation Authority |
|---|---|---|
| Model type | Open weights | inferred |
| Reasoning | No | faq |
| Input modalities | GLM-4.6 (Non-reasoning) supports text input. | faq |
| Output modalities | GLM-4.6 (Non-reasoning) supports text output. | faq |
| Context window | 200k tokens | faq |
| Open weights / source | Yes, GLM-4.6 (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting. | faq |
| Parameters | GLM-4.6 (Non-reasoning) has 357 billion parameters (32 billion active). | faq |
| Active parameters | GLM-4.6 (Non-reasoning) is a Mixture of Experts (MoE) model with 357 billion total parameters, but only 32 billion active parameters are used during inference. | faq |
| License | GLM-4.6 (Non-reasoning) is released under the MIT license. This license allows commercial use. | faq |
| API availability | Yes, GLM-4.6 (Non-reasoning) is available via API through 2 providers. | faq |
Evidence charts
Profile visualizations
Charts are the same canonical evidence cards previously published for this slug, contained inside the D18D page grammar.
AA-Omniscience Index
AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Openness Index: Score
Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open) · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Output Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
End-to-End Response Time
Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Latency: Time To First Answer Token
Seconds to first answer token received · Accounts for reasoning model 'thinking' time · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Latency includes thinking / reasoning time when applicable. Lower is better for interactive use cases.
Context Window
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.
Cost per Intelligence Index Task
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost per Task
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost to Run Artificial Analysis Intelligence Index
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Pricing: Cache Hit, Input, and Output
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Time per Intelligence Index Task
Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Model Size: Total and Active Parameters
Comparison between total model parameters and parameters active during inference · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Larger models generally perform better but cost more to serve. Active parameter count matters for inference efficiency.
Methodology
Methodology & Provenance
This page is rendered from the normalized profile and page JSON for GLM-4.6.
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.
Frequently Asked Questions
Model FAQs & Technical Disclosures
GLM-4.6 (Non-reasoning) was released on September 30, 2025.
GLM-4.6 (Non-reasoning) was created by Z AI.
GLM-4.6 (Non-reasoning) scores 23 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 17).
GLM-4.6 (Non-reasoning) generates output at 43.8 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 58.7 t/s).
GLM-4.6 (Non-reasoning) has a time to first token (TTFT) of 3.62s (based on the median across providers serving the model), which is at the higher end compared to other open weight non-reasoning models of similar size (median: 2.28s).
GLM-4.6 (Non-reasoning) costs $0.57 per 1M input tokens (better than average, median: $0.60) and $2.20 per 1M output tokens (better than average, median: $2.40), based on the median across providers serving the model.
GLM-4.6 (Non-reasoning) costs $0.57 per 1M input tokens and $2.20 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.74 per 1M tokens. Pricing may vary by provider.
No, GLM-4.6 (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
GLM-4.6 (Non-reasoning) supports text input.
GLM-4.6 (Non-reasoning) supports text output.
No, GLM-4.6 (Non-reasoning) does not support image input. It can only process text.
No, GLM-4.6 (Non-reasoning) is not multimodal. It only supports text input.
GLM-4.6 (Non-reasoning) has a context window of 200k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, GLM-4.6 (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
GLM-4.6 (Non-reasoning) has 357 billion parameters (32 billion active).
GLM-4.6 (Non-reasoning) is a Mixture of Experts (MoE) model with 357 billion total parameters, but only 32 billion active parameters are used during inference.
GLM-4.6 (Non-reasoning) is released under the MIT license. This license allows commercial use.
GLM-4.6 (Non-reasoning) achieves a score of 23 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, GLM-4.6 (Non-reasoning) is available via API through 2 providers.
GLM-4.6 (Non-reasoning) is available through 2 API providers.