The Model Index
Models/Zhipu

GLM-5.3-Flash

ZhipuReleased 20 Aug 2026Open
CompareRun it yourself →Announcement
158146–169Index score#45 of 229 models
3/ 8Core tests taken3 of 6 areas · plus 8 anchor tests
−29Versus the frontier at releasebest then: Claude Opus 5
$0.15/ $0.50Price per million tokensinput / output, list price
1.05MContext windowtokens it reads at once

Where it sitson the frontier

Gemini 3 Pro reached this score 9 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond
90%
Humanity's Last Exam
no result
Mathsevidence
FrontierMath T1-3
56%
Codingevidence
SWE-bench Verified
no result
Terminal-Bench
no result
Agentsevidence
APEX-Agents
53%
Novel problemsno evidence yet
ARC-AGI-2
no result
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#45of 219 · 158
LMArena · Mathsmaths questions in chat#14of 373 · 1500LMArena · Codingcoding questions in chat#25of 383 · 1523Artificial Analysis Intelligence Indexoverall capability across ten evaluations#16of 207 · 42LMArena · Textoverall chat quality, judged by people#35of 388 · 1474LMArena · Visionunderstanding images#21of 149 · 1281LMArena · Creative writingcreative writing#59of 386 · 1435Epoch Capabilities Indexoverall capability from many benchmarks#42of 239 · 151.9LMArena · WebDevbuilding web apps and front ends#22of 123 · 1615

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

Not in the top three among current models on any category we track.

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 31 · per million tokens, in / out

OOpenInference$0.020 / $0.30 · fp4cheapestDDeepInfra$0.075 / $0.25 · fp4↗NNovita$0.084 / $0.28 · fp8↗SStreamLake$0.087 / $0.29 · fp8↗GGMICloud$0.090 / $0.30 · fp8↗RRelace$0.035 / $0.50↗SSail Research$0.045 / $0.60 · fp4↗IInferenceNet$0.050 / $0.60 · fp4↗

Run it yourself

🤗Official weightszai-org/GLM-5.3-Flash↗

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

Released20 Aug 2026
Announcementhuggingface.co ↗
Release entryGLM-5.3-Flash
Scored asGLM-5.3-Flash
Artificial Analysis index42
Output speed45 tokens/s

Zhipu releasesaround this one

GLM-5.2Open
index 158
GLM-5.3Open
index 167
GLM-5.3-FlashOpen
index 158