Skip to content

Zhipu AI · Chat

GLM 5.2

Zhipu AI 🇨🇳ChatGLM familyOne of its sources says the weights aren't publicly available.The maker currently plans to deprecate it within the next 180 days (4 Feb 2027). Plans can change.

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

From Empiriolabs's listing:
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

🤗 zai-org/GLM-5.2-FP8753B params Model architecture, as its sources state it llminfo IQ 133.9, ranked among chat models. From 361 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 113.3, 95% interval 105–122. From 31 benchmark families across 15 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 (45.9). Costs more per task than its benchmark results predict. From 50 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 (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. By effort: default 58 · none 48 · high 53 · max 58.Median 35,036 output tokens per task at default effort.How the Yap score worksReleased 16 Jun 2026Maker HQ: CN (source)
All rankings: #15 in Wikipedia pageviews this week #29 on OpenRouter today #30 on OpenRouter this month #32 on NanoGPT recently #34 on OpenRouter this weekAll rankings: #15 in Wikipedia pageviews this week #29 on OpenRouter today #30 on OpenRouter this month #32 on NanoGPT recently #34 on OpenRouter this weekSources: LMArena data, Ambient data, EmpirioLabs data, ModelRunner.ai data, flex.ai API data, LiteLLM data, Morpheus Inference Marketplace data, Hugging FacePrimary data from LMArena from Ambient: name from EmpirioLabs: primary mode, description from ModelRunner.ai: weights availability from flex.ai API: hugging face id from LiteLLM: deprecation date from Morpheus Inference Marketplace: architecture, parameter count from Hugging Face: release date
Tags from its sources:instructreasoningtoolslong-contextcodingfunction-calling

Advantages and trade-offs

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

Advantages

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.

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
Images
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingWeb search

Listings

 Aihubmixcoding-glm-5.2-free · coding, freeSource: AIHubMix data docs1M$0.00$0.00——
 Unorouterglm-5.2:free · freeSource: Models.dev data1M$0.00$0.00——
 OpenRouterInference by Streamlakez-ai/glm-5.2 · fp8Source: OpenRouter data docs1M$0.28cache read $0.052$0.88412,023ms
 Kenariglm-5-2Source: Models.dev data1M$0.2857cache read $0.0531$3.43——
 NanoGPTInference by StreamlakeRegions: 🇨🇳 CNz-ai/glm-5.2 · fp8Source: NanoGPTNot published by the provider$0.294cache read $0.0546$0.92451.72,183ms
 Hugging FaceInference by Relacezai-org/GLM-5.2Source: Hugging Face Inference Providers data1M$0.31$2.40——
 Nous Portalz-ai/glm-5.2:batch · batchSource: Nous Portal Inference Gateway data1M$0.322cache read $0.109$0.989——
 Boundlessglm-5.2Source: Models.dev data1M$0.34cache read $0.17$2.30——
 Avianz-ai/glm-5.2Source: Avian.io Models data1M$0.495cache read $0.124$1.733——
 Iteracomputez-ai/glm-5.2Source: Models.dev data1M$0.53cache read $0.12$1.72——

18 listings without a price are hidden.

Included in plans

Umans Code ProumansSubscription$20/moslows down past the allowancePlan page
Umans Code MaxumansSubscription$50/moslows down past the allowancePlan 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.

Agentic

Arena AgentSource: LMArena data
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026
GAIA4 results
Source: GAIA Leaderboard data · Jul 2026
Difficulty level
Difficulty not reported
MCP Atlas2 results
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
public 500-task subset · think mode · 10-minute timeout
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SWE-Bench Pro3 results
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenHands · tailored prompt · 400K context · 32K max output
Reported by SpaceXAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Source: OpenRouter benchmark exports
16 Jun 2026 version · 90-day results
Across 32 providers lowest 68% median 70.2% highest 77.4%OpenRouter's automatic routing 70.6%
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
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
best reported harness · Claude Code 2.1.167 · 5-run mean · 128K max output
Terminus-2 · parser=json · 256K context · 4h timeout
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Human preference

Arena ELO52 related benchmarks · 52 results
Source: LMArena data · Nov 2026
BenchmarkMax
Arena ELO
Chinese
Creative Writing
English
Show 48 more benchmarksHide 48 benchmarks
BenchmarkMax
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Business and Management and Financial Operations
Industry Entertainment and Sports and Media
Industry Life and Physical and Social Science
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Industry Writing and Literature and Language
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian
Spanish
Style-Controlled
Text Factuality
Text Factuality - Chinese
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - French
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Business and Management and Financial Operations
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Life and Physical and Social Science
Text Factuality - Industry Mathematical
Text Factuality - Industry Medicine and Healthcare
Text Factuality - Industry Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Japanese
Text Factuality - Korean
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Polish
Text Factuality - Russian
Text Factuality - Spanish
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Coding

Arena ELOSource: LMArena data · Nov 2026
FrontierSWE2 results
Source: LLM Stats data
Setting not stated
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Dominance · 1M context · max effort · 128K output · as of 2026-06-16
NL2RepoSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
SWE-Marathon7 related benchmarks · 8 results
SWE-Marathon
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
1M context · max effort · 128K output
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SWE-rebench 2026-03
Source: SWE-rebench
SWE-rebench 2026-04
Source: SWE-rebench
SWE-rebench 2026-05
Source: SWE-rebench
Show 1 more resultHide 1 result
SWE-rebench 2026-06
Source: SWE-rebench
ValsSource: Vals AI

Science

CritPT4 results
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Setting not stated
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond37 results
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Setting not stated
Source: OpenRouter benchmark exports
16 Jun 2026 version · 90-day results
Across 32 providers lowest 78.7% median 84.9% highest 90.6%OpenRouter's automatic routing 85.1%
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

Reasoning

Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
text-only subset · temperature=1 · top_p=.95 · max generation 163,840
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Toolathlon VerifiedTool-Decathlon official evaluation service · 128K max tokens · Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Multilingual

Math

HMMT 20255 related benchmarks · 5 results
HMMT 2025
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
HMMT 2026 Feb
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
GPT-5.5 medium judge
HMMT Feb 26
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Hmmt Feb 2026
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
HMMT Nov 25
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
GPT-5.5 medium judge
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
GPT-5.5 medium judge
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Long context

Factuality

Instruction following

Safety

PhareSource: Phare

Vision

Knowledge

Speech

Other

AIME26GPT-5.5 medium judge · Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSWE v1.12 results
Reported by SpaceXAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Datacurve mini-swe-agent harness
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
mini-swe-agent · official pier framework · 400K context · 2h timeout
E-Commerce Bench7 related benchmarks · 14 results
Mean final assets
Reported by E-Commerce Bench authors / Alibaba Qwen · via BenchBoard docs
Reasoning effort · benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · exact API snapshot not stated for unversioned labels
AnchorRatio · repeat-order pricing
Reported by E-Commerce Bench authors / Alibaba Qwen · via BenchBoard docs
Reasoning effort · benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · exact API snapshot not stated for unversioned labels
BadSpend · fraudulent-supplier spend
Reported by E-Commerce Bench authors / Alibaba Qwen · via BenchBoard docs
Reasoning effort · benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · exact API snapshot not stated for unversioned labels
Controllable return
Reported by E-Commerce Bench authors / Alibaba Qwen · via BenchBoard docs
Reasoning effort · benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · exact API snapshot not stated for unversioned labels
CSE+ · honest-deal negotiation
Reported by E-Commerce Bench authors / Alibaba Qwen · via BenchBoard docs
Reasoning effort · benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · exact API snapshot not stated for unversioned labels
Drawdown / peak assets
Reported by E-Commerce Bench authors / Alibaba Qwen · via BenchBoard docs
Reasoning effort · benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · exact API snapshot not stated for unversioned labels
Show 2 more resultsHide 2 results
Yuan per tool call
Reported by E-Commerce Bench authors / Alibaba Qwen · via BenchBoard docs
Reasoning effort · benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · exact API snapshot not stated for unversioned labels
ExploitGym on-target exploits4 related benchmarks · 6 results
ExploitGym on-target exploits
Source: ExploitGym leaderboard data docs · Aug 2026
By eval · agent: Claude Code · version: unstated · focus: model
agent: DoGNAVY, eval: selected subset, version: v1, focus: agent
(kernel)
Source: ExploitGym leaderboard data docs · Aug 2026
agent: DoGNAVY, eval: selected subset, version: v1, focus: agent
(userspace)
Source: ExploitGym leaderboard data docs · Aug 2026
agent: DoGNAVY, eval: selected subset, version: v1, focus: agent
(V8)
Source: ExploitGym leaderboard data docs · Aug 2026
agent: DoGNAVY, eval: selected subset, version: v1, focus: agent
Horangi36 related benchmarks · 36 results
Nejumi 428 related benchmarks · 56 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
Show 44 more resultsHide 44 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_表現
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
z-ai/glm-5.2: openrouter-reasoning-xhigh
zai-org/GLM-5.2: reasoning-max
NL2Repo-BenchReported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SkillsBench · Vals6 related benchmarks · 6 results
With Skills · Accuracy
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=zai/glm-5.2 · provider=Zhipu AI · reasoning_effort=max · temperature=1 · top_p=0.95 · max_output_tokens=131072
With Skills · Mean cost / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=zai/glm-5.2 · provider=Zhipu AI · reasoning_effort=max · temperature=1 · top_p=0.95 · max_output_tokens=131072
With Skills · Mean duration / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=zai/glm-5.2 · provider=Zhipu AI · reasoning_effort=max · temperature=1 · top_p=0.95 · max_output_tokens=131072
Without Skills · Accuracy
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=zai/glm-5.2 · provider=Zhipu AI · reasoning_effort=max · temperature=1 · top_p=0.95 · max_output_tokens=131072
Without Skills · Mean cost / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=zai/glm-5.2 · provider=Zhipu AI · reasoning_effort=max · temperature=1 · top_p=0.95 · max_output_tokens=131072
Without Skills · Mean duration / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=zai/glm-5.2 · provider=Zhipu AI · reasoning_effort=max · temperature=1 · top_p=0.95 · max_output_tokens=131072
WildClawBench6 related benchmarks · 6 results
WildClawBench
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Multimodal (26 tasks)
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · multimodal-input split · 26 tasks
Overall
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · full 60-task suite
Pure-text (34 tasks)
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · pure-text split · 34 tasks
Total Cost
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · full 60-task suite
Total Elapsed
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · full 60-task suite

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