Z.ai (Zhipu), open weights
GLM-4.5
GLM-4.5 by Z.ai (Zhipu) ranks 122nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.0. Its strongest category is multilingual, where it ranks 77th. API pricing starts at $0.60 per million input tokens and $2.20 per million output tokens, with a 131K-token context window.
Last verified
Specifications
- Noometry rank
- #122 of 354
- Index score
- 42.0
- Evidence
- Confirmed 27 results
- Provider
- Z.ai (Zhipu)
- Released
- July 27, 2025
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 131K
- Max output
- 98K
- Input price
- $0.60 / M
- Output price
- $2.20 / M
- Blended price
- $1 / M
- Output speed
- 32 tokens/s Kagi
- Value
- #109 of 219
- Knowledge cutoff
- April 2025
- Input
- text
- Hugging Face
- zai-org/GLM-4.5
Category scores
Each category score combines every public result we have in that category.
- Coding 41.4
- Reasoning 28.6
- Math 39.0
- Knowledge 35.9
- Multilingual 52.8
- Instruction Following 74.1
- Long Context 38.2
- Writing & Preference 57.5
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 41.4 | #125 | 3 |
| Reasoning | 28.6 | #100 | 2 |
| Math | 39.0 | #116 | 1 |
| Knowledge | 35.9 | #179 | 3 |
| Multilingual | 52.8 | #77 | 1 |
| Instruction Following | 74.1 | #104 | 1 |
| Long Context | 38.2 | #201 | 2 |
| Writing & Preference | 57.5 | #127 | 5 |
Strengths and weaknesses
Categories where GLM-4.5 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 |
|---|---|---|---|
| Multilingual | 52.8 | +5.4 | #77 of 297, top 26% |
| Reasoning | 28.6 | +5.0 | #100 of 350, top 29% |
| Instruction Following | 74.1 | +2.8 | #104 of 305, top 35% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Long Context | 38.2 | −2.7 | #201 of 296, top 68% |
| Knowledge | 35.9 | −1.5 | #179 of 314, top 58% |
| Writing & Preference | 57.5 | +3.7 | #127 of 312, top 41% |
Closest competitors
The models ranked just above and below GLM-4.5. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Amazon Nova Experimental Chat 10 20 | #118 | 42.1 | — | — | Compare |
| Qwen3.5 122B-A10B | #119 | 42.1 | $1.10 | — | Compare |
| Longcat Flash Chat | #120 | 42.1 | — | 69 | Compare |
| Solar Pro4 | #121 | 42.1 | $0.52 | — | Compare |
| Qwen3.5 35B-A3B | #123 | 42.0 | $0.69 | — | Compare |
| GLM-4.7 | #124 | 42.0 | $1 | — | Compare |
| GPT-5.4 nano | #125 | 41.9 | $0.46 | 19 | Compare |
| Amazon Nova Experimental Chat 10 09 | #126 | 41.9 | — | — | 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 |
|---|---|---|---|---|---|
| SWE-bench Verified (bash only) | 54.2% | #25 of 39, top 65% | SWE-bench | 2025-08-22 | |
| WeirdML | 40.6% | #76 of 119, top 64% | thinking | Epoch AI | |
| LMArena Coding | 1434 | #105 of 294, top 36% | LMArena | 2026-10-08 | |
| ALE-Bench | 344.82 | #94 of 105, top 90% | Epoch AI | ||
| AlgoTune | 1.52 | #10 of 18, top 56% | thinking | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Kagi LLM Benchmark | 57.9% | #45 of 99, top 46% | Kagi LLM Benchmark | ||
| LMArena Hard Prompts | 1429 | #90 of 297, top 31% | LMArena | 2026-10-08 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1427 | #91 of 285, top 32% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Humanity's Last Exam | 8.3% | #26 of 41, top 64% | Epoch AI | ||
| Confabulations (lower is better) | 11.3% | #4 of 51, top 8% | Lech Mazur benchmarks | ||
| LMArena Expert | 1433 | #92 of 273, top 34% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1417 | #77 of 297, top 26% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1465 | #79 of 285, top 28% | LMArena | 2026-10-08 | |
| LMArena French | 1418 | #104 of 223, top 47% | LMArena | 2026-10-08 | |
| LMArena German | 1407 | #89 of 231, top 39% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1415 | #45 of 211, top 22% | LMArena | 2026-10-08 | |
| LMArena Korean | 1380 | #78 of 213, top 37% | LMArena | 2026-10-08 | |
| LMArena Russian | 1414 | #90 of 283, top 32% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1454 | #44 of 226, top 20% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1404 | #98 of 298, top 33% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Fiction.LiveBench | 58.3% | #30 of 47, top 64% | Epoch AI | ||
| LMArena Longer Query | 1412 | #104 of 291, top 36% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1430 | #78 of 297, top 27% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1395 | #87 of 295, top 30% | LMArena | 2026-10-08 | |
| Short-Story Creative Writing | 73.4% | #29 of 39, top 75% | Epoch AI | ||
| EQ-Bench Creative Writing | 1343 | #75 of 115, top 66% | EQ-Bench | ||
| LMArena Multi-Turn | 1415 | #102 of 295, top 35% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| openrouter | $0.60 | $2.20 | $0.11 | 2026-10-10 |
| zai | $0.60 | $2.20 | $0.11 | 2026-10-10 |
Compare GLM-4.5
- GLM-4.5 vs Solar Pro4
- GLM-4.5 vs Qwen3.5 35B-A3B
- GLM-4.5 vs Longcat Flash Chat
- GLM-4.5 vs GLM-4.7
- GLM-4.5 vs Qwen3.5 122B-A10B
- GLM-4.5 vs GPT-5.4 nano
- GLM-4.5 vs GPT-6 Astra
- GLM-4.5 vs Claude Fable 5.1
- GLM-4.5 vs Gemini 3.8 Flash
- GLM-4.5 vs Kimi K3
- GLM-4.5 vs Grok 4.6
- GLM-4.5 vs Qwen3.8 Max
- GLM-4.5 vs Muse Spark 1.3
- GLM-4.5 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-4.742.0
- GLM-4.641.4
Frequently asked questions
How good is GLM-4.5?
GLM-4.5 by Z.ai (Zhipu) ranks 122nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.0. Its strongest category is multilingual, where it ranks 77th. API pricing starts at $0.60 per million input tokens and $2.20 per million output tokens, with a 131K-token context window.
How much does GLM-4.5 cost?
GLM-4.5 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-4.5's context window?
GLM-4.5 accepts up to 131K tokens of input and can write up to 98K tokens in one response.
Is GLM-4.5 open source?
Yes. GLM-4.5's weights are downloadable from Hugging Face (zai-org/GLM-4.5); check the license for commercial terms.
How fast is GLM-4.5?
GLM-4.5 generated about 32 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.
What are GLM-4.5's strengths and weaknesses?
Relative to other ranked models, GLM-4.5 places best in multilingual, reasoning, instruction following and lowest in long context, knowledge, writing & preference.
What is GLM-4.5 best at?
Its best category is multilingual, where it ranks 77th on Noometry.