Z.ai (Zhipu), open weights

# GLM-4.6

> GLM-4.6 by Z.ai (Zhipu), released September 2025. Ranked #135 of 354 with a Noometry Index of 41.4. API: $0.60 in / $2.20 out per M tokens. 205K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/glm-4-6
- Last updated: 2026-10-10
- Title: GLM-4.6 Benchmarks, Price & Rank (October 2026) | Noometry

GLM-4.6 by Z.ai (Zhipu) ranks 135th of 354 ranked models on the Noometry Index as of October 2026, with a score of 41.4. Its strongest category is agentic & tool use, where it ranks 66th. API pricing starts at $0.60 per million input tokens and $2.20 per million output tokens, with a 205K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #135 of 354
- **Index score:** 41.4
- **Evidence:** Confirmed 29 results
- **Provider:** [Z.ai (Zhipu)](https://noometry.com/providers/zai)
- **Released:** September 30, 2025
- **Weights:** Open weights
- **Reasoning:** Yes
- **Context window:** 205K
- **Max output:** 131K
- **Input price:** $0.60 / M
- **Output price:** $2.20 / M
- **Blended price:** $1 / M
- **Output speed:** 12 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** #113 of 219
- **Knowledge cutoff:** April 2025
- **Input:** text
- **Hugging Face:** [zai-org/GLM-4.6](https://huggingface.co/zai-org/GLM-4.6)

## Category scores

Each category score combines every public result we have in that category.

GLM-4.6 category scores

1.  Coding 40.1
2.  Agentic & Tool Use 32.3
3.  Reasoning 23.7
4.  Math 39.1
5.  Knowledge 40.2
6.  Multilingual 53.5
7.  Instruction Following 74.3
8.  Long Context 43.4
9.  Writing & Preference 61.1
10.  020406080

GLM-4.6 category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 40.1 | #148 | 4 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 32.3 | #66 | 2 |
| [Reasoning](https://noometry.com/best/reasoning) | 23.7 | #172 | 3 |
| [Math](https://noometry.com/best/math) | 39.1 | #111 | 1 |
| [Knowledge](https://noometry.com/best/knowledge) | 40.2 | #124 | 2 |
| [Multilingual](https://noometry.com/best/multilingual) | 53.5 | #66 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 74.3 | #98 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 43.4 | #94 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 61.1 | #90 | 4 |

## Strengths and weaknesses

Categories where GLM-4.6 places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

GLM-4.6: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Multilingual](https://noometry.com/best/multilingual) | 53.5 | +6.1 | #66 of 297, top 23% |
| [Writing & Preference](https://noometry.com/best/writing) | 61.1 | +7.3 | #90 of 312, top 29% |
| [Long Context](https://noometry.com/best/long-context) | 43.4 | +2.5 | #94 of 296, top 32% |

### Weakest categories

GLM-4.6: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 23.7 | +0.1 | #172 of 350, top 50% |
| [Coding](https://noometry.com/best/coding) | 40.1 | +1.4 | #148 of 340, top 44% |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 32.3 | +2.0 | #66 of 154, top 43% |

## Closest competitors

The models ranked just above and below GLM-4.6. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to GLM-4.6
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Muse Glimmer](https://noometry.com/models/muse-glimmer) | #131 | 41.7 | — | — | [Compare](https://noometry.com/compare/glm-4-6-vs-muse-glimmer) |
| [o4-mini](https://noometry.com/models/o4-mini) | #132 | 41.6 | $1.93 | 6 | [Compare](https://noometry.com/compare/glm-4-6-vs-o4-mini) |
| [Gemini 3.5 Flash Lite](https://noometry.com/models/gemini-3-5-flash-lite) | #133 | 41.5 | $0.85 | — | [Compare](https://noometry.com/compare/gemini-3-5-flash-lite-vs-glm-4-6) |
| [Grok 4.1](https://noometry.com/models/grok-4-1) | #134 | 41.5 | — | — | [Compare](https://noometry.com/compare/glm-4-6-vs-grok-4-1) |
| [Grok 4.1 Fast](https://noometry.com/models/grok-4-1-fast) | #136 | 41.4 | $0.28 | — | [Compare](https://noometry.com/compare/glm-4-6-vs-grok-4-1-fast) |
| [GLM-4.6V](https://noometry.com/models/glm-4-6v) | #137 | 41.3 | $0.45 | — | [Compare](https://noometry.com/compare/glm-4-6-vs-glm-4-6v) |
| [MiMo-V2-Flash](https://noometry.com/models/mimo-v2-flash) | #138 | 41.3 | $0.18 | — | [Compare](https://noometry.com/compare/glm-4-6-vs-mimo-v2-flash) |
| [Hunyuan Turbos 20250226](https://noometry.com/models/hunyuan-turbos) | #139 | 41.3 | — | — | [Compare](https://noometry.com/compare/glm-4-6-vs-hunyuan-turbos) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

GLM-4.6 Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [SWE-bench Verified (bash only)](https://noometry.com/benchmarks/swe-bench-bash-only) | 55.4% | #23 of 39, top 59% |  | [SWE-bench](https://www.swebench.com/) | 2025-12-01 |
| [LMArena WebDev](https://noometry.com/benchmarks/arena-webdev) | 1340 | #90 of 113, top 80% |  | [LMArena](https://lmarena.ai/leaderboard/webdev) | 2026-10-08 |
| [SciCode](https://noometry.com/benchmarks/scicode) | 38.4% | #88 of 121, top 73% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1449 | #87 of 294, top 30% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [ALE-Bench](https://noometry.com/benchmarks/ale-bench) | 340.82 | #95 of 105, top 91% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Agentic & Tool Use

GLM-4.6 Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Terminal-Bench](https://noometry.com/benchmarks/terminal-bench) | 24.5% | #35 of 41, top 86% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Berkeley Function Calling Leaderboard](https://noometry.com/benchmarks/bfcl) | 72.4% | #4 of 49, top 9% | fc thinking | [Berkeley Function Calling Leaderboard](https://gorilla.cs.berkeley.edu/leaderboard.html) |  |

### Reasoning

GLM-4.6 Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 45.7% |  |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 47.4% | #69 of 99, top 70% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 1.1% | #80 of 134, top 60% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1440 | #81 of 297, top 28% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Math

GLM-4.6 Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1432 | #80 of 285, top 29% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [FrontierMath (Feb 2025 set)](https://noometry.com/benchmarks/frontiermath-2025-02) | 3.8% | #51 of 68, top 75% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-08 |
| [FrontierMath Tier 4 (v1)](https://noometry.com/benchmarks/frontiermath-tier-4-v1) | 2.1% | #36 of 55, top 66% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-08 |

### Knowledge

GLM-4.6 Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) (lower is better) | 9.5% | #50 of 96, top 53% |  | [Vectara Hallucination Leaderboard](https://github.com/vectara/hallucination-leaderboard) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1431 | #95 of 273, top 35% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multilingual

GLM-4.6 Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1426 | #66 of 297, top 23% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1499 | #45 of 285, top 16% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1459 | #53 of 223, top 24% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1447 | #48 of 231, top 21% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1393 | #66 of 211, top 32% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1400 | #53 of 213, top 25% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1419 | #83 of 283, top 30% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1436 | #71 of 226, top 32% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

GLM-4.6 Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1410 | #87 of 298, top 30% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

GLM-4.6 Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1422 | #87 of 291, top 30% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

GLM-4.6 Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1440 | #62 of 297, top 21% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1411 | #62 of 295, top 22% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 1411 | #71 of 115, top 62% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1427 | #87 of 295, top 30% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

GLM-4.6 API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [deepinfra](https://deepinfra.com/models) | $0.50 | $2 | $0.10 | 2026-10-10 |
| [openrouter](https://openrouter.ai/z-ai/glm-4.6) | $0.50 | $2 | $0.10 | 2026-10-10 |
| [zai](https://docs.z.ai/guides/overview/pricing) | $0.60 | $2.20 | $0.11 | 2026-10-10 |

[All Z.ai (Zhipu) API prices →](https://noometry.com/llm-pricing/zai) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare GLM-4.6

-   [GLM-4.6 vs GLM-4.5V](https://noometry.com/compare/glm-4-5v-vs-glm-4-6)
-   [GLM-4.6 vs Grok 4.1](https://noometry.com/compare/glm-4-6-vs-grok-4-1)
-   [GLM-4.6 vs Grok 4.1 Fast](https://noometry.com/compare/glm-4-6-vs-grok-4-1-fast)
-   [GLM-4.6 vs Gemini 3.5 Flash Lite](https://noometry.com/compare/gemini-3-5-flash-lite-vs-glm-4-6)
-   [GLM-4.6 vs GLM-4.6V](https://noometry.com/compare/glm-4-6-vs-glm-4-6v)
-   [GLM-4.6 vs o4-mini](https://noometry.com/compare/glm-4-6-vs-o4-mini)
-   [GLM-4.6 vs MiMo-V2-Flash](https://noometry.com/compare/glm-4-6-vs-mimo-v2-flash)
-   [GLM-4.6 vs GPT-6 Astra](https://noometry.com/compare/glm-4-6-vs-gpt-6-astra)
-   [GLM-4.6 vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-glm-4-6)
-   [GLM-4.6 vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-glm-4-6)
-   [GLM-4.6 vs Kimi K3](https://noometry.com/compare/glm-4-6-vs-kimi-k3)
-   [GLM-4.6 vs Grok 4.6](https://noometry.com/compare/glm-4-6-vs-grok-4-6)
-   [GLM-4.6 vs Qwen3.8 Max](https://noometry.com/compare/glm-4-6-vs-qwen3-8-max)
-   [GLM-4.6 vs Muse Spark 1.3](https://noometry.com/compare/glm-4-6-vs-muse-spark-1-3)

## Other Z.ai (Zhipu) models

-   [GLM-5.3](https://noometry.com/models/glm-5-3)54.8
-   [GLM-5.3-Flash](https://noometry.com/models/glm-5-3-flash)51.8
-   [GLM-5.2](https://noometry.com/models/glm-5-2)51.1
-   [GLM-5.1](https://noometry.com/models/glm-5-1)47.8
-   [GLM-5](https://noometry.com/models/glm-5)46.1
-   [GLM-5V-Turbo](https://noometry.com/models/glm-5v-turbo)43.8
-   [GLM-4.5](https://noometry.com/models/glm-4-5)42.0
-   [GLM-4.7](https://noometry.com/models/glm-4-7)42.0

## Frequently asked questions

### How good is GLM-4.6?

GLM-4.6 by Z.ai (Zhipu) ranks 135th of 354 ranked models on the Noometry Index as of October 2026, with a score of 41.4. Its strongest category is agentic & tool use, where it ranks 66th. API pricing starts at $0.60 per million input tokens and $2.20 per million output tokens, with a 205K-token context window.

### How much does GLM-4.6 cost?

GLM-4.6 costs $0.60 per million input tokens and $2.20 per million output tokens on Z.ai (Zhipu)'s own API, with cached input at $0.11.

### What is GLM-4.6's context window?

GLM-4.6 accepts up to 205K tokens of input and can write up to 131K tokens in one response.

### Is GLM-4.6 open source?

Yes. GLM-4.6's weights are downloadable from Hugging Face (zai-org/GLM-4.6); check the license for commercial terms.

### How fast is GLM-4.6?

GLM-4.6 generated about 12 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are GLM-4.6's strengths and weaknesses?

Relative to other ranked models, GLM-4.6 places best in multilingual, writing & preference, long context and lowest in reasoning, coding, agentic & tool use.

### What is GLM-4.6 best at?

Its best category is agentic & tool use, where it ranks 66th on Noometry.

### Cite this page

Noometry. (2026). GLM-4.6 benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/glm-4-6

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/glm-4-6.md).