Z.ai (Zhipu), open weights
GLM-5.1
GLM-5.1 by Z.ai (Zhipu) ranks 59th of 354 ranked models on the Noometry Index as of October 2026, with a score of 47.8. Its strongest category is writing & preference, where it ranks 31st. API pricing starts at $1.40 per million input tokens and $4.40 per million output tokens, with a 200K-token context window.
Last verified
Specifications
- Noometry rank
- #59 of 354
- Index score
- 47.8
- Evidence
- Confirmed 41 results
- Provider
- Z.ai (Zhipu)
- Released
- April 7, 2026
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 200K
- Max output
- 131K
- Input price
- $1.40 / M
- Output price
- $4.40 / M
- Blended price
- $2.15 / M
- Output speed
- Not measured
- Value
- #148 of 219
- Knowledge cutoff
- April 2025
- Input
- text
- Hugging Face
- zai-org/GLM-5.1
Category scores
Each category score combines every public result we have in that category.
- Coding 48.7
- Agentic & Tool Use 24.9
- Reasoning 39.1
- Math 49.7
- Knowledge 54.9
- Multilingual 55.0
- Instruction Following 76.3
- Long Context 44.9
- Writing & Preference 66.9
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 48.7 | #55 | 5 |
| Agentic & Tool Use | 24.9 | #113 | 3 |
| Reasoning | 39.1 | #60 | 6 |
| Math | 49.7 | #60 | 5 |
| Knowledge | 54.9 | #50 | 3 |
| Multilingual | 55.0 | #36 | 1 |
| Instruction Following | 76.3 | #42 | 1 |
| Long Context | 44.9 | #53 | 1 |
| Writing & Preference | 66.9 | #31 | 4 |
Strengths and weaknesses
Categories where GLM-5.1 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 |
|---|---|---|---|
| Writing & Preference | 66.9 | +13.2 | #31 of 312, top 10% |
| Multilingual | 55.0 | +7.5 | #36 of 297, top 13% |
| Instruction Following | 76.3 | +5.0 | #42 of 305, top 14% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Agentic & Tool Use | 24.9 | −5.5 | #113 of 154, top 74% |
| Math | 49.7 | +13.1 | #60 of 327, top 19% |
| Long Context | 44.9 | +3.9 | #53 of 296, top 18% |
Closest competitors
The models ranked just above and below GLM-5.1. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| MiMo-V2.6-Flash | #55 | 48.5 | $0.18 | — | Compare |
| Grok 4 | #56 | 48.1 | — | 1 | Compare |
| Kimi K2.5 | #57 | 48.1 | $0.90 | 66 | Compare |
| Step 5 Preview | #58 | 47.9 | $1.43 | — | Compare |
| Kimi K2.6 | #60 | 47.7 | $1.71 | — | Compare |
| o3 | #61 | 47.5 | $3.50 | 3 | Compare |
| Qwen3.6 Plus | #62 | 47.5 | $1.13 | — | Compare |
| Inkling-Small | #63 | 46.5 | $0.64 | — | 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 | 74.2% | #16 of 32, top 50% | Epoch AI | 2026-05-15 | |
| LMArena WebDev | 1508 | #47 of 113, top 42% | LMArena | 2026-10-08 | |
| SciCode | 43.8% | #62 of 121, top 52% | Epoch AI | ||
| WeirdML | 57.1% | #36 of 119, top 31% | Epoch AI | ||
| LMArena Coding | 1485 | #37 of 294, top 13% | LMArena | 2026-10-08 | |
| ALE-Bench | 887.1 | #52 of 105, top 50% | Epoch AI |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| APEX-Agents | 40.9% | #36 of 49, top 74% | Epoch AI | ||
| ExploitBench | 18.1% | #7 of 9, top 78% | Epoch AI | ||
| GBAEval | 0% | #22 of 23, top 96% | Epoch AI | ||
| Vending-Bench 2 | 5,634 | #23 of 60, top 39% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| SimpleBench | 55.1% | #34 of 77, top 45% | Epoch AI | ||
| NYT Connections (extended) | 77.7% | #40 of 91, top 44% | Lech Mazur benchmarks | ||
| CritPt | 4.6% | #59 of 134, top 45% | Epoch AI | ||
| Chess Puzzles | 19% | #62 of 129, top 49% | Epoch AI | 2026-08-10 | |
| Thematic Generalization | 69.8% | #6 of 23, top 27% | Lech Mazur benchmarks | ||
| LMArena Hard Prompts | 1472 | #37 of 297, top 13% | LMArena | 2026-10-08 | |
| Epoch Capabilities Index | 149.84 | #55 of 213, top 26% | Epoch AI | 2026-04-07 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | #54 of 81, top 67% | Epoch AI | 2026-08-29 | |
| FrontierMath (Tiers 1-3) | 24.9% | none | Epoch AI | 2026-08-28 | |
| MathArena Final-Answer Competitions | 67.1% | #17 of 29, top 59% | MathArena | ||
| OTIS Mock AIME 2024-2025 | 93.3% | #41 of 173, top 24% | Epoch AI | 2026-08-10 | |
| ProofBench | 22.2% | #45 of 77, top 59% | Epoch AI | ||
| LMArena Math | 1473 | #36 of 285, top 13% | LMArena | 2026-10-08 | |
| FrontierMath (Feb 2025 set) | 33.4% | #15 of 68, top 23% | Epoch AI | 2026-05-11 | |
| FrontierMath Tier 4 (v1) | 12.5% | #17 of 55, top 31% | Epoch AI | 2026-05-12 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 89.9% | #39 of 186, top 21% | Epoch AI | 2026-08-10 | |
| SimpleQA Verified | 34% | #51 of 77, top 67% | Epoch AI | 2026-08-27 | |
| LMArena Expert | 1476 | #46 of 273, top 17% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1447 | #36 of 297, top 13% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1515 | #30 of 285, top 11% | LMArena | 2026-10-08 | |
| LMArena French | 1474 | #32 of 223, top 15% | LMArena | 2026-10-08 | |
| LMArena German | 1465 | #31 of 231, top 14% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1434 | #31 of 211, top 15% | LMArena | 2026-10-08 | |
| LMArena Korean | 1418 | #36 of 213, top 17% | LMArena | 2026-10-08 | |
| LMArena Russian | 1454 | #39 of 283, top 14% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1469 | #27 of 226, top 12% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1451 | #40 of 298, top 14% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1466 | #35 of 291, top 13% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1461 | #33 of 297, top 12% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1453 | #27 of 295, top 10% | LMArena | 2026-10-08 | |
| EQ-Bench Creative Writing | 1592 | #43 of 115, top 38% | EQ-Bench | ||
| LMArena Multi-Turn | 1472 | #27 of 295, top 10% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| deepinfra | $1.05 | $3.50 | $0.20 | 2026-10-10 |
| openrouter | $0.97 | $3.04 | $0.18 | 2026-10-10 |
| together | $1.40 | $4.40 | $0.26 | 2026-10-10 |
| zai | $1.40 | $4.40 | $0.26 | 2026-10-10 |
Compare GLM-5.1
Other Z.ai (Zhipu) models
- GLM-5.354.8
- GLM-5.3-Flash51.8
- GLM-5.251.1
- GLM-546.1
- GLM-5V-Turbo43.8
- GLM-4.542.0
- GLM-4.742.0
- GLM-4.641.4
Frequently asked questions
How good is GLM-5.1?
GLM-5.1 by Z.ai (Zhipu) ranks 59th of 354 ranked models on the Noometry Index as of October 2026, with a score of 47.8. Its strongest category is writing & preference, where it ranks 31st. API pricing starts at $1.40 per million input tokens and $4.40 per million output tokens, with a 200K-token context window.
How much does GLM-5.1 cost?
GLM-5.1 costs $1.40 per million input tokens and $4.40 per million output tokens on Z.ai (Zhipu)'s own API, with cached input at $0.26.
What is GLM-5.1's context window?
GLM-5.1 accepts up to 200K tokens of input and can write up to 131K tokens in one response.
Is GLM-5.1 open source?
Yes. GLM-5.1's weights are downloadable from Hugging Face (zai-org/GLM-5.1); check the license for commercial terms.
What are GLM-5.1's strengths and weaknesses?
Relative to other ranked models, GLM-5.1 places best in writing & preference, multilingual, instruction following and lowest in agentic & tool use, math, long context.
What is GLM-5.1 best at?
Its best category is writing & preference, where it ranks 31st on Noometry.