GLM-4.6 is the latest version of Z.ai's flagship model, bringing significant improvements over GLM-4.5. Key features include: 200K token context window (expanded from 128K), superior coding performance with better real-world application in Claude Code/Cline/Roo Code/Kilo Code, advanced reasoning with tool use during inference, stronger agent capabilities, and refined writing aligned with human preferences. GLM-4.6 achieves competitive performance with DeepSeek-V3.2-Exp and Claude Sonnet 4, reaching near parity with Claude Sonnet 4 (48.6% win rate) on CC-Bench real-world coding tasks.
发布日期2025年9月30日
参数规模357B
上下文长度205K
许可证MIT
知识截止—
Benchmarks
评测成绩
| 评测基准 | 类别 | 分数 | 来源 |
|---|---|---|---|
| AIME 2025 | math reasoning | 93.9 | 来源 |
| 开源模型能力榜·AIME2025 | general | 90.3 | 来源 |
| 开源模型能力榜·IFEval | general | 88.7 | 来源 |
| 开源模型能力榜·MMLU-Pro | general | 83.0 | 来源 |
| LiveCodeBench v6 | reasoning general | 82.8 | 来源 |
| GPQA | reasoning general | 81.0 | 来源 |
| 开源模型能力榜·GPQA-Diamond | general | 80.4 | 来源 |
| 开源模型能力榜·LiveCodeBenchV6 | general | 78.2 | 来源 |
| 开源模型能力榜 | general | 73.3 | 来源 |
| SWE-bench-Verified | reasoning frontend_development code | 68.0 | 来源 |
| BrowseComp | reasoning search | 45.1 | 来源 |
| Terminal-Bench | reasoning code | 40.5 | 来源 |
| 开源模型能力榜·HLE | general | 19.3 | 来源 |
| HLE | reasoning math | 17.2 | 来源 |
Pricing
API 价格对比
| 服务商 | 输入价 | 输出价 | 上下文 | 吞吐(tok/s) | 延迟(s) | 函数调用 | 代码执行 | 联网搜索 |
|---|---|---|---|---|---|---|---|---|
| iFlow | $0.00 | $0.00 | 200K | — | — | ✓ | ✗ | ✗ |
| 302.AI | $0.29 | $1.14 | 205K | — | — | ✓ | ✗ | ✗ |
| Helicone | $0.45 | $1.50 | 205K | — | — | ✓ | ✗ | ✗ |
| LLM Gateway | $0.55 | $2.20 | 205K | — | — | ✓ | ✗ | ✗ |
| OpenCode Zen | $0.60 | $2.20 | 205K | — | — | ✓ | ✗ | ✗ |
| Z.AI | $0.60 | $2.20 | 205K | — | — | ✓ | ✗ | ✗ |
| Zhipu AI | $0.60 | $2.20 | 205K | — | — | ✓ | ✗ | ✗ |
价格单位：美元/百万 token，数据来自社区整理，仅供参考。