GLM-5

Z.ai
Arena score
1446
Among open models
#11of 148
Among all on Arena
#62
Votes
28,979

Measured on GLM-5, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.

Score by category

Top 10 among open models in#8Chinese#9Multi-turn#9Korean#10Creative writing

CategoryScore
  • Chinese1512
  • Coding1462
  • Software & IT1460
  • Science1460
  • Hard prompts, English1460
  • French1457
  • English1457
  • Multi-turn1456
  • Expert1455
  • Medicine & health1454
  • Spanish1454
  • Legal & government1454
  • Hard prompts1452
  • Applied math1450
  • German1447
  • Long prompts1446
  • Excluding ties1443
  • Math1439
  • Creative writing1437
  • Russian1437
  • Writing & literature1436
  • Polish1433
  • Non-English1431
  • Business & finance1431
  • Instructions1428
  • Media & sports1426
  • Korean1419
  • Japanese1414

Score by size

Plot against
Best for its size

About as strong, smaller

Compare

Discussion

Built on it

Quantizations
19
Fine-tunes
38
Adapters
10
Merges
1

Ways to run it

Most downloaded

BenchClub runs

Not runnable yet

Runs open once a GLM-5 build is registered.

More from Z.ai

See more

Other >300B models

See more