The Model Index
Models/Zhipu

GLM-5.2

ZhipuReleased 16 Jun 2026OpenDate verified
CompareRun it yourself →Announcement
158147–169Index score#44 of 229 models
4/ 8Core tests taken4 of 6 areas · plus 16 anchor tests
−27Versus the frontier at releasebest then: Claude Fable 5Replaced by GLM-5.3
$1.4/ $4.4Price per million tokensinput / output, list price
1.05MContext windowtokens it reads at once

Where it sitson the frontier

Gemini 3 Pro reached this score 7 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond
92%
Humanity's Last Exam
no result
Mathsevidence
FrontierMath T1-3
59%
Codingevidence
SWE-bench Verified
79%
Terminal-Bench
no result
Agentsevidence
APEX-Agents
no result
Novel problemsevidence
ARC-AGI-2
23%
Long tasksno evidence yet
METR time horizon
no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

What others sayrank on each leaderboard

The Model Indexindependent tests, our method#44of 219 · 158
LMArena · Mathsmaths questions in chat#27of 373 · 1487LMArena · Creative writingcreative writing#28of 386 · 1455LMArena · Textoverall chat quality, judged by people#29of 388 · 1475LMArena · Codingcoding questions in chat#50of 383 · 1512Epoch Capabilities Indexoverall capability from many benchmarks#44of 239 · 151.8LMArena · WebDevbuilding web apps and front ends#23of 123 · 1605

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.

Best attop three among current models

1stSWE-bench VerifiedEpoch AI · independent

Where this model places in the top three of today's models, on category leaderboards and on our core tests.

Where to use itprices checked 1 Oct 2026

From the lab

Z.ai Chatapp · subscription↗Z.ai APIAPI↗

API providers 26 · per million tokens, in / out

BBaidu$0.24 / $0.85 · fp4cheapestSStreamLake$0.56 / $1.76 · fp8↗DDeepInfra$0.56 / $1.8 · fp4↗RReka$0.70 / $1.4↗MMorph$0.28 / $2.69 · fp8↗DDecart$2.25 / $8.0 · fp4↗NNovita$0.65 / $2.04 · fp8↗DDigitalOcean$0.70 / $2.2↗

Run it yourself

🤗Official weightszai-org/GLM-5.2↗

Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps.

Facts and sources

Released16 Jun 2026
Announcementz.ai ↗
Release entryGLM-5.2
Scored asGLM-5.2
Artificial Analysis index–
Output speed–

Zhipu releasesaround this one

GLM-5Open
index 144
GLM-5.1Open
index 153
GLM-5.2Open
index 158
GLM-5.3Open
index 167
GLM-5.3-FlashOpen
index 158