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-4.6
GLM-4.6 is an open-weight model from Z.ai, released Sep 30, 2025. It ranks #75 of 351 on the LMArena text leaderboard with a rating of 1440. It costs $0.55 per million input tokens and $2.20 per million output tokens, with a 200K-token context window.
- Developer
- Z.ai (Zhipu AI)
- Released
- Sep 30, 2025
- Context window
- 200K
- Price in / out, per 1M tokens
- $0.55 / $2.20
- Weights
- Open · MIT
- Inputs
- Text
- Reasoning
- Yes
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 22.4K
- Hugging Face likes
- 1.2K
The rating LMArena published at each update since Oct 3, 2025. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| Vibe Code BenchCoding | 3.09% | 107 / 115 | $10.85 | |
| LiveCodeBenchCoding | 81.04% | 65 / 143 | $0.6 / $2.2 | |
| MedQAMedicine | 92.22% | 33 / 92 | $0.6 / $2.2 | |
| GPQA DiamondReasoning | 74.50% | 86 / 138 | $0.6 / $2.2 | |
| MMLU-ProReasoning | 82.20% | 81 / 138 | $0.6 / $2.2 | |
| AIMEReasoning | 92.71% | 17 / 96 | $0.6 / $2.2 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1440 | 75 / 351 | 35.8K |
| CodingLMArena | 1449 | 105 / 346 | 7.6K |
| MathLMArena | 1432 | 98 / 339 | 2.2K |
| Creative writingLMArena | 1412 | 79 / 349 | 5.1K |
| Instruction followingLMArena | 1410 | 106 / 351 | 10.3K |
| Hard promptsLMArena | 1440 | 96 / 351 | 19.4K |
| Multi-turnLMArena | 1427 | 107 / 349 | 5.6K |
| Long queriesLMArena | 1422 | 106 / 330 | 9.1K |
| ExpertLMArena | 1432 | 114 / 305 | 2.1K |
| Legal and governmentIndustries | 1448 | 69 / 325 | 2.5K |
| Medicine and healthcareIndustries | 1455 | 64 / 325 | 1.9K |
| Business and financeIndustries | 1416 | 112 / 344 | 6.9K |
| ChineseLanguages | 1499 | 53 / 328 | 2.7K |
| SpanishLanguages | 1437 | 89 / 249 | 1K |
| GermanLanguages | 1447 | 59 / 261 | 681 |
| FrenchLanguages | 1459 | 67 / 252 | 706 |
| JapaneseLanguages | 1393 | 87 / 236 | 373 |
| WebDevLMArena | 1341 | 122 / 124 | 6.8K |
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-4.6
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-4.6?
GLM-4.6 is made by Z.ai (Zhipu AI), founded 2019 and based in Beijing.
How much does GLM-4.6 cost?
$0.55 per million input tokens and $2.20 per million output tokens, at its provider’s list price.
What is GLM-4.6’s context window?
200K tokens (204,800).
How does GLM-4.6 rank?
#75 of 351 on LMArena’s text leaderboard, rated 1440 (95% interval 1436–1444) from 35,818 votes, as of Oct 22, 2026.
Is GLM-4.6 open source?
GLM-4.6 has open weights under the MIT license, downloadable from Hugging Face (zai-org/GLM-4.6).