/Tech5h ago

Zai_org's open-weights GLM-5.2 tops the Design Arena coding leaderboard with a 1360 Elo, surpassing Claude Fable 5

The model gained 27 Elo points to climb four positions

1418374026K

#121

Original post

elvis@omarsar0

Impressive if true!

Better than Claude Fable 5? Wow!

Design is really lacking in these frontier models, so I'm very curious to test GLM-5.2 myself.

Testing this already on a few internal use cases and will report back on findings.

Design Arena@Designarena

BREAKING: GLM-5.2 is now 1st on Design Arena.

With an Elo of 1360, GLM-5.2 has jumped ahead of the now unavailable Claude Fable 5.

And it's open weights.

This is an improvement of 4 positions and 27 Elo points to achieve one of the highest Elo scores in our code categories since Design Arena started.

Huge congratulations to the @Zai_org on the release!

12:31 PM · Jun 16, 2026 · 12.6K Views

Sentiment

Many users praised GLM-5.2 for topping the Design Arena Code Leaderboard with strong coding results and expressed eagerness to test it themselves, while one dismissed the benchmark as meaningless.

Pos

87.5%

Neg

12.5%

7 comments with sentiment.

Cluster Engagement

Digg Deeper

No Digg Deeper questions have been answered for this story yet.

Posts from X

Most Activity

VIEWS3.7KBOOKMARKS6REPLIES2

elvis@omarsar0

Looks strong at SWE too.

11h3.7K96

LIKES9

elvis@omarsar0

Damn! That looks nice.

11h2.3K95

RETWEETS1

Diana@sdianahu

woah first time oss models are leading

Design Arena@Designarena

BREAKING: GLM-5.2 is now 1st on Design Arena.

With an Elo of 1360, GLM-5.2 has jumped ahead of the now unavailable Claude Fable 5.

And it's open weights.

This is an improvement of 4 positions and 27 Elo points to achieve one of the highest Elo scores in our code categories since Design Arena started.

Huge congratulations to the @Zai_org on the release!

3h8.9K6211

Arindam Majumder 𝕏@Arindam_1729

@omarsar0 Tried it myself!

Pretty solid, gonna test it more on coding tasks

10h8921

michelle@michellechen

@weswinder already up! launch partner :) https://developers.cloudflare.com/workers-ai/models/glm-5.2/

10h322

Wes Winder@weswinder

@michellechen is cloudflare gonna serve it?

10h84

NotMissing@notmissing_

@omarsar0 Have to test it immediately

10h361

Native AI@NativeAIAgency

@omarsar0 Must be delusional to think this benchmark tells anything.

10h581

Jason Gilbertson@jgilbertson47

@omarsar0 Remarkable if it holds up in real use. How is the testing going?

7h26

Wes Winder@weswinder

@michellechen 👀👀

10h15

Hossein Kazemi@hossein761

@omarsar0 Looking solid no?

11h11

That AI Guy@LewisWeldtech

@omarsar0 It's true, see my 1.6 hypothesis.

6h3

michelle@michellechen

woah

Design Arena@Designarena

BREAKING: GLM-5.2 is now 1st on Design Arena.

With an Elo of 1360, GLM-5.2 has jumped ahead of the now unavailable Claude Fable 5.

And it's open weights.

This is an improvement of 4 positions and 27 Elo points to achieve one of the highest Elo scores in our code categories since Design Arena started.

Huge congratulations to the @Zai_org on the release!

10h4.8K363