Skip to content

Zhipu AI · Chat

GLM 4.7

Zhipu AI 🇨🇳ChatGLM familyOpen weights. One of its sources says the weights are publicly available.The maker lists this model as deprecated (16 Oct 2026).

Newer version: GLM 5.3. We compared release dates and version names in our catalogue.

From Neosantara's listing:
Latest generation GLM model with improved reasoning and coding.
llminfo IQ
127.0
Market median price
$0.865 blended / 1M
Max context
32M
Listings
105

Evidence and sources

🤗 zai-org/GLM-4.7358B params Model architecture, as its sources state it llminfo IQ 127.0, ranked among chat models. From 234 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 103.5, 95% interval 98–109. From 12 benchmark families across 9 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (41.0). Costs more per task than its benchmark results predict. From 27 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsChatty (61 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 37,425 output tokens per task at default effort.How the Yap score worksReleased 22 Dec 2025Maker HQ: CN (source)
All rankings: #49 on NanoGPT recently #124 on OpenRouter today #142 on OpenRouter this week #146 on OpenRouter this monthSources: Writer Pricing, Mancer data, LiteLLM data, Models.dev data, AI/ML API data, Morpheus Inference Marketplace data, Neosantara Inference data, Hugging FacePrimary data from Writer Pricing from Mancer: architecture from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode from Morpheus Inference Marketplace: parameter count from Neosantara Inference: description from Hugging Face: release date
Tags from its sources:open-sourcemultilinguallong-contextfunction-callingreasoning

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (16 Oct 2026).

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured outputPrompt cachingWeb searchBatch API

Listings

 Aihubmixcoding-glm-4.7-free · coding, freeSource: AIHubMix data docs200K$0.00$0.00———
 NanoGPTInference by MeganovaRegions: 🇺🇸 USz-ai/glm-4.7 · fp8Source: NanoGPTNot published by the provider$0.2625$1.05———
 Zenmuxz-ai/glm-4.7Sources: Models.dev data, ZenMux data200K$0.2911cache read $0.0582$1.1645$0.01——
 Zhipu AI (Open Platform)glm-4.7Source: Zhipu BigModel Open Platform Pricing200K———
 Ppiozai-org/glm-4.7Source: PPIO data205K———
 OpenRouterInference by DeepInfraz-ai/glm-4.7 · fp4/flex · fp4Source: OpenRouter data docs203K$0.32cache read $0.064$1.40—421,645.5ms
 Avianz-ai/glm-4.7Source: Avian.io Models data203K$0.388cache read $0.097$1.806———
 Fastrouterz-ai/glm-4.7Source: FastRouter data203K$0.40cache read $0.08$1.75———
 Hugging FaceInference by DeepInfrazai-org/GLM-4.7Source: Hugging Face Inference Providers data203K$0.40$1.75———
 Kiloz-ai/glm-4.7Sources: Kilo AI Gateway data, Models.dev data203K$0.40cache read $0.08$1.75———
Show all 95 listings

Showing 10 of 95: the cheapest per 1M input tokens from each provider. 2 listings with suspiciously low prices are in the full list only.

Also sold by 302ai, Abacus, Amazon Web Services, Baseten, Crossmodel, DeepInfra, Dinference, Eden AI, Eurouter, Fireworks AI, Flowdot, Gmicloud, Google, Impossibl, Ionet, Jiekou, Llmgateway, Llmgateway Providers, Mancer, Meganova, Merge Gateway, Moark, Neosantara, Nous Portal, Novita AI, Ofox, Openroute Cn, Orcarouter, Qiniu, Requesty, Together AI, Venice, Vercel, Writer, Z.ai.

10 listings without a price are hidden.

Included in plans

Coding Plan ProAlibaba CloudSubscription$50/moPlan page
BytePlus Coding Plan LiteBytePlusSubscription$10/moPlan page
BytePlus Coding Plan ProBytePlusSubscription$50/moPlan page
GLM Coding Plan LitezhipuSubscription$18/moPlan page
GLM Coding Plan ProzhipuSubscription$72/moPlan page
GLM Coding Plan MaxzhipuSubscription$160/moPlan page

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO42 related benchmarks · 42 results
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Coding

Arena ELOSource: LMArena data · Nov 2026
SWE-bench Verified7 related benchmarks · 7 results
SWE-bench Verified
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
SWE-bench Multilingual
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Show 1 more resultHide 1 result

Agentic

OpenHandsSource: OpenHands Index data
Tau-benchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Source: OpenRouter benchmark exports
22 Dec 2025 version · 90-day results
Across 7 providers lowest 68% median 71.3% highest 75.5%OpenRouter's automatic routing 72%
Show results from 7 providers and OpenRouter's automatic routingHide results from 7 providers and OpenRouter's automatic routing
  • Google
  • Novita
  • OpenRouter's automatic routing
  • Venice
  • AtlasCloud
  • DeepInfra
  • Z.AI
  • StreamLake

Multilingual

Reasoning

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond10 results
Source: OpenEvals Leaderboard data · Reported by the model's developer. The source relaying it did not verify it. · Mar 2026
Setting not stated
Source: OpenRouter benchmark exports
22 Dec 2025 version · 90-day results
Across 8 providers lowest 60.8% median 83.2% highest 84.5%OpenRouter's automatic routing 83.4%
Show results from 8 providers and OpenRouter's automatic routingHide results from 8 providers and OpenRouter's automatic routing
  • Z.AI
  • Novita
  • Google
  • AtlasCloud
  • OpenRouter's automatic routing
  • StreamLake
  • DeepInfra
  • Venice
  • Mancer 2

Vision

Math

AIME 2025Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Factuality

General

Instruction following

Knowledge

MMLU-ProSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Other

Horangi36 related benchmarks · 36 results
Nejumi 428 related benchmarks · 28 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
Show 22 more resultsHide 22 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_表現
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
zai-org/GLM-4.7: reasoning-enabled

Data credits: Data by LLM Stats · SEA-HELM leaderboard, AI Singapore (AI Products team), National University of Singapore. Published aggregate scores; results licence not stated (SEA-HELM code is MIT). · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · LMArena, CC BY 4.0 (licence) · Steel.dev Agent Leaderboards, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · CyberGym leaderboard (Wang, Shi, He, Cai, Zhang, Song; UC Berkeley), ICLR 2026. Results evaluated and submitted by the listed teams. No licence is stated for the result data; the repository's Apache-2.0 licence covers its code only. · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · OpenEvals/leaderboard-data, MIT (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · MineBench, MIT (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · OpenHands Index (All Hands AI), Apache-2.0 (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · Vectara Hallucination Leaderboard, Apache-2.0 (licence)

Also known as: alicloud-glm-4.7, baseten/zai-org/glm-4.7, bedrock/ap-northeast-1/zai.glm-4.7, bedrock/ap-south-1/zai.glm-4.7, bedrock/ap-southeast-2/zai.glm-4.7, bedrock/ap-southeast-3/zai.glm-4.7, bedrock/eu-central-1/zai.glm-4.7, bedrock/eu-north-1/zai.glm-4.7, bedrock/eu-south-1/zai.glm-4.7, bedrock/eu-west-1/zai.glm-4.7, bedrock/eu-west-2/zai.glm-4.7, bedrock/sa-east-1/zai.glm-4.7, bedrock_mantle/ap-northeast-1/zai.glm-4.7, bedrock_mantle/ap-south-1/zai.glm-4.7, bedrock_mantle/ap-southeast-2/zai.glm-4.7, bedrock_mantle/ap-southeast-3/zai.glm-4.7, bedrock_mantle/eu-north-1/zai.glm-4.7, bedrock_mantle/eu-west-2/zai.glm-4.7, bedrock_mantle/sa-east-1/zai.glm-4.7, bedrock_mantle/zai.glm-4.7, cc-glm-4.7, coding-glm-4.7, coding-glm-4.7-free, deepinfra/zai-org/glm-4.7, fireworks_ai/accounts/fireworks/models/glm-4p7, fireworks_ai/glm-4p7, glm 4.7, glm-4-7, glm-4-7-251222, glm-4.7-free, glm-4p7, gmi/zai-org/glm-4.7-fp8, novita/glm-4.7, novita/zai-org/glm-4.7, pro/zai-org/glm-4.7, sophnet/glm-4.7, thudm/glm-4.7, together-ai/glm-4.7, together_ai/zai-org/glm-4.7, vertex_ai/zai-org/glm-4.7-maas, z-ai/glm-4.7, z-ai/glm-4.7-original, z-ai/glm-4.7-original:thinking, z-ai/glm-4.7:thinking, z.ai/glm-4.7, zai-org-glm-4.7, zai-org/glm-4.7, zai-org/glm-4.7-fp4, zai-org/glm-4.7-fp8, zai-org/glm-4.7-maas, zai.glm-4.7, zai/glm-4.7, zhipu/glm-4.7

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works