Z.ai (Zhipu), open weights
GLM-4.6V
GLM-4.6V by Z.ai (Zhipu) ranks 137th of 354 ranked models on the Noometry Index as of October 2026, with a score of 41.3. Its strongest category is multimodal, where it ranks 90th. API pricing starts at $0.30 per million input tokens and $0.90 per million output tokens, with a 128K-token context window.
Last verified
Specifications
- Noometry rank
- #137 of 354
- Index score
- 41.3
- Evidence
- Confirmed 12 results
- Provider
- Z.ai (Zhipu)
- Released
- December 8, 2025
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 128K
- Max output
- 33K
- Input price
- $0.30 / M
- Output price
- $0.90 / M
- Blended price
- $0.45 / M
- Output speed
- Not measured
- Value
- #69 of 219
- Knowledge cutoff
- April 2025
- Input
- text, image, video
- Hugging Face
- zai-org/GLM-4.6V
Category scores
Each category score combines every public result we have in that category.
- Coding 40.9
- Reasoning 27.6
- Knowledge 38.0
- Multimodal 34.8
- Multilingual 48.6
- Instruction Following 71.4
- Long Context 41.3
- Writing & Preference 56.6
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 40.9 | #128 | 1 |
| Reasoning | 27.6 | #115 | 1 |
| Knowledge | 38.0 | #149 | 1 |
| Multimodal | 34.8 | #90 | 1 |
| Multilingual | 48.6 | #141 | 1 |
| Instruction Following | 71.4 | #151 | 1 |
| Long Context | 41.3 | #143 | 1 |
| Writing & Preference | 56.6 | #137 | 3 |
Strengths and weaknesses
Categories where GLM-4.6V places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Reasoning | 27.6 | +4.0 | #115 of 350, top 33% |
| Coding | 40.9 | +2.2 | #128 of 340, top 38% |
| Writing & Preference | 56.6 | +2.8 | #137 of 312, top 44% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Multimodal | 34.8 | −3.8 | #90 of 128, top 71% |
| Instruction Following | 71.4 | +0.1 | #151 of 305, top 50% |
| Long Context | 41.3 | +0.4 | #143 of 296, top 49% |
Closest competitors
The models ranked just above and below GLM-4.6V. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Gemini 3.5 Flash Lite | #133 | 41.5 | $0.85 | — | Compare |
| Grok 4.1 | #134 | 41.5 | — | — | Compare |
| GLM-4.6 | #135 | 41.4 | $1 | 12 | Compare |
| Grok 4.1 Fast | #136 | 41.4 | $0.28 | — | Compare |
| MiMo-V2-Flash | #138 | 41.3 | $0.18 | — | Compare |
| Hunyuan Turbos 20250226 | #139 | 41.3 | — | — | Compare |
| Kimi K2 (Jul 2025) | #140 | 41.2 | $1 | 201 | Compare |
| Grok-3 mini | #141 | 41.2 | — | 10 | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
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
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Coding | 1390 | #143 of 294, top 49% | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1368 | #148 of 297, top 50% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1371 | #141 of 273, top 52% | LMArena | 2026-10-08 |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 1164 | #94 of 122, top 78% | LMArena | 2026-10-09 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1359 | #141 of 297, top 48% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1425 | #124 of 285, top 44% | LMArena | 2026-10-08 | |
| LMArena Russian | 1340 | #152 of 283, top 54% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1352 | #145 of 298, top 49% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1358 | #148 of 291, top 51% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1377 | #140 of 297, top 48% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1347 | #131 of 295, top 45% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1360 | #149 of 295, top 51% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| openrouter | $0.30 | $0.90 | $0.055 | 2026-10-10 |
| zai | $0.30 | $0.90 | — | 2026-10-10 |
Compare GLM-4.6V
- GLM-4.6V vs GLM-4.6
- GLM-4.6V vs Grok 4.1 Fast
- GLM-4.6V vs MiMo-V2-Flash
- GLM-4.6V vs Hunyuan Turbos 20250226
- GLM-4.6V vs Grok 4.1
- GLM-4.6V vs Kimi K2 (Jul 2025)
- GLM-4.6V vs GPT-6 Astra
- GLM-4.6V vs Claude Fable 5.1
- GLM-4.6V vs Gemini 3.8 Flash
- GLM-4.6V vs Kimi K3
- GLM-4.6V vs Grok 4.6
- GLM-4.6V vs Qwen3.8 Max
- GLM-4.6V vs Muse Spark 1.3
- GLM-4.6V vs DeepSeek V4 Pro
Other Z.ai (Zhipu) models
- GLM-5.354.8
- GLM-5.3-Flash51.8
- GLM-5.251.1
- GLM-5.147.8
- GLM-546.1
- GLM-5V-Turbo43.8
- GLM-4.542.0
- GLM-4.742.0
Frequently asked questions
How good is GLM-4.6V?
GLM-4.6V by Z.ai (Zhipu) ranks 137th of 354 ranked models on the Noometry Index as of October 2026, with a score of 41.3. Its strongest category is multimodal, where it ranks 90th. API pricing starts at $0.30 per million input tokens and $0.90 per million output tokens, with a 128K-token context window.
How much does GLM-4.6V cost?
GLM-4.6V costs $0.30 per million input tokens and $0.90 per million output tokens on Z.ai (Zhipu)'s own API.
What is GLM-4.6V's context window?
GLM-4.6V accepts up to 128K tokens of input and can write up to 33K tokens in one response.
Is GLM-4.6V open source?
Yes. GLM-4.6V's weights are downloadable from Hugging Face (zai-org/GLM-4.6V); check the license for commercial terms.
What are GLM-4.6V's strengths and weaknesses?
Relative to other ranked models, GLM-4.6V places best in reasoning, coding, writing & preference and lowest in multimodal, instruction following, long context.
What is GLM-4.6V best at?
Its best category is multimodal, where it ranks 90th on Noometry.