Model dossier模型档案

GLM 5.2

GLM 5.2 is a high-tier model from Z.ai (Intelligence Score 85.4/100). Strongest in math (99.3) and knowledge (96); best fit: quantitative and scientific work. It trails in agent (37.7). Mid-priced: $0.650 in / $2.04 out per 1M tokens. Context window 1M tokens — long-document friendly. Open weights — self-hostable. Reachable via CN-direct endpoints.

GLM 5.2 是 Z.ai 的高水平梯队模型(智能评分 85.4/100)。最强项是数学(99.3分),其次是知识(96分);适合数理与科研任务。短板是智能体(37.7分)。定价属中档定价:每百万 token 输入 $0.650 / 输出 $2.04。上下文 1M token,长文档友好。开放权重,可自托管。支持国内直连。

open weights开放权重 ⌂ CN direct国内直连

85.4

Intelligence Score · benchmark coverage 智能评分 · benchmark 覆盖 95%

◈

Benchmark scoresBenchmark 成绩

10 entries 条

Benchmark基准	Score成绩	Index指数	Dated日期	Measured by测评方
Humanity's Last ExamReasoning	54.7	95	2026-08-12	official官方榜	source ↗×6⚠±14.6
GPQA DiamondReasoning	91.2	96	2026-07-18	3rd-party第三方	source ↗×9⚠±3.8
MMLU-ProKnowledge	88.9	96	2026-07	3rd-party第三方	source ↗×3
SWE-bench VerifiedCoding	62.1	65	2026-08	3rd-party第三方	source ↗×7⚠±19
AIME 2025Math	98.6	99	2026-07-17	3rd-party第三方	source ↗×6
LiveCodeBenchCoding	69.5	74	—	3rd-party第三方	source ↗×2
FrontierMathMath	94	100	—	3rd-party第三方	source ↗
Terminal-BenchCoding	81	88	—	3rd-party第三方	source ↗×5
τ²-benchAgent	37.11⚡max	38	2026-08-04	official官方榜	source ↗×5⚠±61.99
LMArena (Chatbot Arena)Preference	1471	62	2026-08-12	official官方榜	source ↗×4

≡

Specs & pricing规格与价格

Provider厂商	Z.ai
Released发布	2026-06-16
Context window上下文	1M tokens
Max output最大输出	131K tokens
Modality模态	text->text
Reasoning tiers推理档位	⚡none ⚡low ⚡medium ⚡high ⚡max default默认 max · none / minimal / low / medium / high / xhigh / max
API input price输入价格	$0.650 / 1M tokens
API output price输出价格	$2.04 / 1M tokens

⛓

Tools using this model使用它的工具

智谱开放平台 BigModel

⚔

Head-to-head正面对比

vs 对比 Kimi K3 vs 对比 Qwen3.7 Max vs 对比 MiniMax M3

How we score →评分方法 → · Catalog & pricing via the official OpenRouter API.模型目录与价格来自 OpenRouter 官方 API。