
GLM-5
GLM-5 is an open-weight model from Z.ai, released Feb 11, 2026. It ranks #59 of 351 on the LMArena text leaderboard with a rating of 1446. It costs $1 per million input tokens and $3.20 per million output tokens, with a 200K-token context window.
- Developer
- Z.ai (Zhipu AI)
- Released
- Feb 11, 2026
- Context window
- 200K
- Price in / out, per 1M tokens
- $1 / $3.20
- Weights
- Open · MIT
- Inputs
- Text
- Reasoning
- Yes
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 1.1M
- Hugging Face likes
- 2.1K
The rating LMArena published at each update since Feb 10, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 71.40% | 55 / 85 | $0.45 | |
| Vibe Code BenchCoding | 23.36% | 78 / 115 | $40.27 | |
| LiveCodeBenchCoding | 81.87% | 59 / 143 | $1 / $3.2 | |
| MedQAMedicine | 94.27% | 18 / 92 | $1 / $3.2 | |
| GPQA DiamondReasoning | 83.33% | 58 / 138 | $1 / $3.2 | |
| MMLU-ProReasoning | 86.03% | 51 / 138 | $1 / $3.2 | |
| AIMEReasoning | 91.67% | 23 / 96 | $1 / $3.2 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1446 | 59 / 351 | 29.3K |
| CodingLMArena | 1461 | 83 / 346 | 7.6K |
| MathLMArena | 1440 | 85 / 339 | 1.7K |
| Creative writingLMArena | 1438 | 51 / 349 | 4.9K |
| Instruction followingLMArena | 1428 | 77 / 351 | 9.6K |
| Hard promptsLMArena | 1452 | 71 / 351 | 18.2K |
| Multi-turnLMArena | 1456 | 52 / 349 | 4.7K |
| Long queriesLMArena | 1446 | 69 / 330 | 11.1K |
| ExpertLMArena | 1454 | 79 / 305 | 2.6K |
| Legal and governmentIndustries | 1454 | 63 / 325 | 2.3K |
| Medicine and healthcareIndustries | 1456 | 60 / 325 | 2.1K |
| Business and financeIndustries | 1430 | 80 / 344 | 5.9K |
| ChineseLanguages | 1511 | 38 / 328 | 2K |
| SpanishLanguages | 1454 | 52 / 249 | 1.1K |
| GermanLanguages | 1447 | 60 / 261 | 511 |
| FrenchLanguages | 1455 | 76 / 252 | 910 |
| JapaneseLanguages | 1417 | 56 / 236 | 275 |
| WebDevLMArena | 1435 | 86 / 124 | 7.5K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare GLM-5
Z.ai (Zhipu AI)
A Tsinghua spin-out that builds the GLM family of open bilingual models. Founded 2019, based in Beijing. z.ai
Questions
Who makes GLM-5?
GLM-5 is made by Z.ai (Zhipu AI), founded 2019 and based in Beijing.
How much does GLM-5 cost?
$1 per million input tokens and $3.20 per million output tokens, at its provider’s list price.
What is GLM-5’s context window?
200K tokens (204,800).
How does GLM-5 rank?
#59 of 351 on LMArena’s text leaderboard, rated 1446 (95% interval 1442–1450) from 29,267 votes, as of Oct 22, 2026.
Is GLM-5 open source?
GLM-5 has open weights under the MIT license, downloadable from Hugging Face (zai-org/GLM-5).
Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview