Skip to content

Zhipu AI · Chat

GLM 4.5

Zhipu AI 🇨🇳ChatGLM familyOpen weights. One of its sources says the weights are publicly available.The maker currently plans to deprecate it within the next 180 days (31 Dec 2026). Plans can change.

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

From Aiml API's listing:
Advanced version of GLM-4.5 with enhanced capabilities and web search integration
llminfo IQ
121.9
Market median price
$1.00 blended / 1M
Max context
131K
Listings
37

Evidence and sources

🤗 zai-org/GLM-4.5llminfo IQ 121.9, ranked among chat models. From 110 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 95.3, 95% interval 88–103. From 10 benchmark families across 7 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 (41.4). Costs more per task than its benchmark results predict. From 21 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 resultsTypical (53 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 13,479 output tokens per task at default effort.How the Yap score worksReleased 20 Jul 2025 Training-data cutoff, as its sources state it Maker HQ: CN (source)
All rankings: #16 in Wikipedia pageviews this week #171 on NanoGPT recently #314 on OpenRouter today #338 on OpenRouter this week #343 on OpenRouter this monthAll rankings: #16 in Wikipedia pageviews this week #171 on NanoGPT recently #314 on OpenRouter today #338 on OpenRouter this week #343 on OpenRouter this monthSources: LMArena data, Models.dev data, AI/ML API data, Kilo AI Gateway data, OpenRouter data docs, Hugging FacePrimary data from LMArena from Models.dev: name, weights availability from AI/ML API: primary mode, description from Kilo AI Gateway: deprecation date from OpenRouter: knowledge cutoff from Hugging Face: release date

Advantages and trade-offs

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

Advantages

Open weights available

The weights are public. 2 of the 9 peers that say either way have open weights.

Trade-offs

Deprecation scheduled

The maker plans to deprecate it on 31 Dec 2026, within the next 180 days.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 8 maker's prices; 2 market median prices.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured outputPrompt caching

Listings

 Submodelzai-org/GLM-4.5-FP8 · fp8Source: Models.dev data131K$0.20$0.80—
 302aiglm-4.5Sources: 302.ai data, Models.dev data128K$0.286$1.142—
 Zenmuxz-ai/glm-4.5Sources: Models.dev data, ZenMux data128K$0.2911cache read $0.0582$1.1645$0.01
 Aihubmixglm-4.5Source: AIHubMix data docs131K$0.40$1.60—
 DeepInfradeepinfra/zai-org/GLM-4.5Source: LiteLLM data131K$0.40$1.60—
 Fireworks AIfireworks_ai/accounts/fireworks/models/glm-4p5Source: LiteLLM data131K$0.55$2.19—
 Openroute Cnglm-4.5Source: OpenRoute CN Marketplace131K—
 Qiniuglm-4.5Sources: Models.dev data, Qiniu AI data, Qiniu AI Model Plaza Pricing131K—
 Z.aiGLM-4.5Sources: LiteLLM data, Models.dev data, Z.AI Pricing128K$0.60cache read $0.11$2.20—
 Flowdotz-ai/glm-4.5Source: FlowDot data131K$0.60$2.20—

4 listings without a price are hidden.

Benchmarks

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

Human preference

Arena ELO27 related benchmarks · 27 results
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Coding

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

Math

MATH-500Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MathArenaSource: MathArena data
ValsSource: Vals AI

Agentic

BFCL-v3Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Long context

Science

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

Reasoning

General

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

Knowledge

Factuality

Instruction following

Vision

Other

ValsSource: Vals AI

Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · ArtifactsBench (Tencent Hunyuan), CC BY 4.0 (licence) · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · LiveMCPBench leaderboard, ICIP-CAS (Mo et al., 2025). Sheet linked from the Apache-2.0 project README; sheet licence not separately stated. · MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence)

Also known as: deepinfra/zai-org/glm-4.5, fireworks_ai/accounts/fireworks/models/glm-4p5, glm-4-5, gmi/zai-org/glm-4.5-fp8, novita/zai-org/glm-4.5, sophnet/glm-4.5, vercel_ai_gateway/zai/glm-4.5, z-ai/glm-4.5, z-ai/glm-4.5:thinking, zai-org/glm-4.5, zai-org/glm-4.5-fp8, zai/glm-4.5, zhipu/glm-4.5, zhipuai/glm-4.5

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