Zhipu AI · Chat
GLM 5.2
Newer version: GLM 5.3. We compared release dates and version names in our catalogue.
Reasoning and coding model with a 1M token context, 128K output, adjustable reasoning effort, native web search, and tool calling.
- llminfo IQ
- 133.9
- Market median price
- $2.15 blended / 1M
- Max context
- 1M
- Listings
- 270
Evidence and sources
Advantages and trade-offs
Compared with 10 chat models, picked mainly by popularity and IQ
Advantages
More provider options
Trade-offs
Deprecation scheduled
The maker plans to deprecate it on 4 Feb 2027, within the next 180 days.
No open weights
The weights aren't public, so you can't run it yourself.
Input & output
as stated by the model's providersCapabilities
Supported operations and provider-stated features
Listings
| 1M | $0.00 | $0.00 | — | — | |
| 1M | $0.00 | $0.00 | — | — | |
| 1M | $0.28cache read $0.052 | $0.88 | 41 | 2,023ms | |
| 1M | $0.2857cache read $0.0531 | $3.43 | — | — | |
| —Not published by the provider | $0.294cache read $0.0546 | $0.924 | 51.7 | 2,183ms | |
| 1M | $0.31 | $2.40 | — | — | |
| 1M | $0.322cache read $0.109 | $0.989 | — | — | |
| 1M | $0.34cache read $0.17 | $2.30 | — | — | |
| 1M | $0.495cache read $0.124 | $1.733 | — | — | |
| 1M | $0.53cache read $0.12 | $1.72 | — | — |
Showing 10 of 252: the cheapest per 1M input tokens from each provider. 13 listings with suspiciously low prices are in the full list only.
Also sold by 302ai, Abacus, Above, Adaption, Aimlapi, Alibaba Cloud, Alibaba Cloud (China), Ambient, Arcee, Atlascloud, Baidu, Baseten, Berget AI, BytePlus, Chutes, Cline Pass, Cloudflare Workers AI, Cometapi, Commandcode, Core42, Cortecs AI, Crossmodel, Crusoe, Databricks, DeepInfra, Digitalocean, Dinference, Doubleword, Eden AI, Empiriolabs, Engy, Eurouter, Evolink, Evroc, Fastrouter, Fireworks AI, Flexai, Flowdot, Friendli AI, Geodd, Gmicloud, Google, Greenpt, Hpc AI, Huawei Maas, Impossibl, Ionet, Jalapeno, Keln, Kilo, Llmgateway, Llmgateway Providers, Meganova, Merge Gateway, Microsoft Azure, Mistral AI, Morph, Nebius AI Studio, Neon, Netmind, Novita AI, Ofox, Ollama, Opencode Go, Openroute Cn, Opper, Orcarouter, Perplexity, Phala, Pioneer, Ppio, Prime, Qiniu, Redpill, Regolo, Requesty, Routing Run, Scx AI, Sference, SiliconFlow, Siliconflow Cn, Standardcompute, Streamlake, Tencent, Tensorix, Tensorx, Together AI, Tokengo, Tokenify, Tokenmix, Tokensmind, Venice, Vercel, Vivgrid, Volcano Engine, Vultr, Wafer, Watt, Wavespeed, Weights & Biases, Z.ai, Zenmux, Zhipu AI (Open Platform).
18 listings without a price are hidden.
Included in plans
Benchmarks
Named effort levels run from lowest to highest. Select a result to see its source details.
Agentic
Show results from 32 providers and OpenRouter's automatic routingHide results from 32 providers and OpenRouter's automatic routing
- Morph
- Makora
- DigitalOcean
- InferenceNet
- Sail Research
- Relace
- AtlasCloud
- Baidu
- Novita
- Friendli
- Alibaba
- Nebius
- OpenRouter's automatic routing
- Wafer
- Fireworks
- SiliconFlow
- Phala
- StreamLake
- DeepInfra
- BaseTen
- Together
- Z.AI
- Reka
- Parasail
- Decart
- Crusoe
- Inceptron
- GMICloud
- CoreWeave
- Ambient
- Mistral
- Venice
- Cloudflare
Human preference
| Benchmark | Max |
|---|---|
| Arena ELO | |
| Chinese | |
| Creative Writing | |
| English |
Show 48 more benchmarksHide 48 benchmarks
Coding
Show 1 more resultHide 1 result
Science
Show results from 32 providers and OpenRouter's automatic routingHide results from 32 providers and OpenRouter's automatic routing
- DeepInfra
- DigitalOcean
- Wafer
- Venice
- Reka
- Inceptron
- Novita
- Fireworks
- BaseTen
- Baidu
- Z.AI
- Decart
- Ambient
- SiliconFlow
- Sail Research
- Alibaba
- OpenRouter's automatic routing
- Nebius
- Together
- AtlasCloud
- Crusoe
- Cloudflare
- Mistral
- CoreWeave
- Parasail
- InferenceNet
- Morph
- Friendli
- StreamLake
- Makora
- Relace
- GMICloud
- Phala
General
| Benchmark | Score |
|---|---|
| typos | |
| AMPS_Hard | |
| connections | |
| consecutive_events |
Show 15 more benchmarksHide 15 benchmarks
| Benchmark | Score |
|---|---|
| integrals_with_game | |
| javascript | |
| logic_with_navigation | |
| olympiad | |
| paraphrase | |
| plot_unscrambling | |
| python | |
| simplify | |
| spatial | |
| story_generation | |
| summarize | |
| tablejoin | |
| tablereformat | |
| theory_of_mind | |
| typescript |
Reasoning
Multilingual
Math
Long context
Factuality
Instruction following
Safety
Vision
Knowledge
Speech
Other
Show 2 more resultsHide 2 results
| Benchmark | glm-5.2: high-effort |
|---|---|
| 4: ALT_환각방지 | |
| 4 subset: haerae_bench_v1_rc | |
| 4 subset: haerae_bench_v1_wo_rc | |
| 4 subset: hrm8k |
Show 32 more benchmarksHide 32 benchmarks
Show 44 more resultsHide 44 results
Show 2 more resultsHide 2 results
Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · 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) · LMArena, CC BY 4.0 (licence) · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · BullshitBench by Peter Gostev, MIT (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Data by LLM Stats · 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) · ExploitGym leaderboard (Wang et al., UC Berkeley), arXiv:2605.11086. No licence is stated for the result data; the repository's Apache-2.0 licence covers its code only, and task data keeps its upstream licences. Literal exploit counts; hidden rows omitted. · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · HalluHard: Fan, Delsad, Flammarion and Andriushchenko (EPFL), arXiv:2602.01031 · 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 · Phare (Giskard), CC BY 4.0 (licence) · Steel.dev Agent Leaderboards, MIT (licence) · Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted.
Also known as: @cf/zai-org/glm-5.2, accounts/fireworks/routers/glm-5p2-fast, alibaba/glm-5.2, azure_ai/fw-glm-5.2, azure_ai/fw-glm-5.2-fast, baseten/zai-org/glm-5.2, baseten/zai-org/glm-5.2-fast, cline-pass/glm-5.2, cloudflare-glm-5.2, cloudflare/@cf/zai-org/glm-5.2, coding-glm-5.2, coding-glm-5.2-free, dashscope/glm-5.2, databricks-glm-5-2, databricks/databricks-glm-5-2, deepinfra/zai-org/glm-5.2, doubleword/glm-5.2, doubleword/glm-5.2:flex, e2ee-glm-5-2-p, empiriolabs/glm-5-2, fireworks/glm-5.2, fireworks_ai/accounts/fireworks/models/glm-5p2, fireworks_ai/accounts/fireworks/routers/glm-5p2-fast, fireworks_ai/accounts/fireworks/routers/glm-5p2-fast-us, fireworks_ai/glm-5p2, fireworks_ai/glm-5p2-fast, fireworks_ai/glm-5p2-fast-us, flexai/glm-5.2, glm 5.2, glm-5-2, glm-5-2-260617, glm-5.2-fast, glm-5.2-max, glm-5.2-nitro, glm-5.2:free, glm-5.2:web, glm-5.2@eu, glm-5p2, glm5-2, glm5.2, gmi/zai-org/glm-5.2-fp8, inceptron/glm-5.2, mistral/glm-5-2, mistral/zai-glm-5-2, modelrunner-ai/z-ai-glm-5.2, nebius/glm-5.2, nebius/zai-org/glm-5.2, novita/glm-5.2, novita/zai-org/glm-5.2, opencode_go/glm-5.2, perplexity/glm-5.2, qwen_ai_platform/glm-5.2, qwencloud/glm-5.2, runware/glm-5.2, scaleway/glm-5.2, scx-ai-gp/glm-5.2, scx-ai-gp/glm-5.2-fast, scx-ai/glm-5.2, sference/glm-5.2, streamlake/glm-5.2, tee/glm-5.2, tee/glm-5.2:thinking, tencent/glm-5.2, tensorx/glm-5.2, together_ai/zai-org/glm-5.2, vertex_ai/zai-org/glm-5.2-maas, wandb/zai-org/glm-5.2, z-ai/glm-5.2, z-ai/glm-5.2-fast, z-ai/glm-5.2:batch, z-ai/glm-5.2:thinking, zai-glm-5-2, zai-org-glm-5-2, zai-org-glm-5.2, zai-org/glm-5.2, zai-org/glm-5.2-fast, zai-org/glm-5.2-fp8, zai-org/glm-5.2-maas, zai-org/glm-5.2-tee, zai/glm-5.2, zai/glm-5.2-fast, zhipu/glm-5-2, zhipu/glm-5.2, zhipuai/glm-5.2
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