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
GLM-5.2
GLM-5.2 is an open-weight model from Z.ai, released Jun 16, 2026. It ranks #32 of 351 on the LMArena text leaderboard with a rating of 1470. It costs $0.034 per million input tokens and $7 per million output tokens, with a 1M-token context window.
- Developer
- Z.ai (Zhipu AI)
- Released
- Jun 16, 2026
- Context window
- 1M
- Price in / out, per 1M tokens
- $0.034 / $7
- Weights
- Open · MIT
- Inputs
- Text
- Reasoning
- Yes
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 322.7K
- Hugging Face likes
- 5.2K
The rating LMArena published at each update since Jun 16, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 82.80% | 17 / 85 | $0.71 | |
| Vibe Code BenchCoding | 63.96% | 51 / 115 | $8.49 | |
| LiveCodeBenchCoding | 69.50% | 93 / 143 | $1.4 / $4.4 | |
| Legal Research BenchLaw | 31.25% | 48 / 85 | $0.89 | |
| MedCodeMedicine | 40.77% | 60 / 107 | $1.4 / $4.4 | |
| GPQA DiamondReasoning | 85.61% | 47 / 138 | $1.4 / $4.4 | |
| MMLU-ProReasoning | 86.71% | 39 / 138 | $1.4 / $4.4 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1470 | 32 / 351 | 52.3K |
| CodingLMArena | 1487 | 42 / 346 | 14K |
| MathLMArena | 1485 | 29 / 339 | 2.4K |
| Creative writingLMArena | 1462 | 24 / 349 | 10.5K |
| Instruction followingLMArena | 1466 | 36 / 351 | 18K |
| Hard promptsLMArena | 1481 | 38 / 351 | 33.9K |
| Multi-turnLMArena | 1469 | 38 / 349 | 8.3K |
| Long queriesLMArena | 1480 | 30 / 330 | 23.8K |
| ExpertLMArena | 1487 | 42 / 305 | 5.5K |
| Legal and governmentIndustries | 1486 | 23 / 325 | 4.2K |
| Medicine and healthcareIndustries | 1475 | 32 / 325 | 3.8K |
| Business and financeIndustries | 1451 | 43 / 344 | 9.9K |
| ChineseLanguages | 1522 | 31 / 328 | 3.8K |
| SpanishLanguages | 1478 | 17 / 249 | 1.6K |
| GermanLanguages | 1471 | 29 / 261 | 935 |
| FrenchLanguages | 1478 | 36 / 252 | 1.9K |
| JapaneseLanguages | 1449 | 34 / 236 | 850 |
| WebDevLMArena | 1604 | 31 / 124 | 17.1K |
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-5.2
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-5.2?
GLM-5.2 is made by Z.ai (Zhipu AI), founded 2019 and based in Beijing.
How much does GLM-5.2 cost?
$0.034 per million input tokens and $7 per million output tokens, at its provider’s list price.
What is GLM-5.2’s context window?
1M tokens (1,048,576).
How does GLM-5.2 rank?
#32 of 351 on LMArena’s text leaderboard, rated 1470 (95% interval 1466–1474) from 52,283 votes, as of Oct 22, 2026.
Is GLM-5.2 open source?
GLM-5.2 has open weights under the MIT license, downloadable from Hugging Face (zai-org/GLM-5.2).