GLM-4.5

Z.ai
Arena score
1430
Among open models
#23of 148
Among all on Arena
#95
Votes
23,746

Measured on GLM-4.5, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.

Score by category

CategoryScore
  • Chinese1465
  • Medicine & health1455
  • Spanish1454
  • Science1445
  • Software & IT1441
  • Legal & government1438
  • English1437
  • Coding1434
  • Expert1433
  • Applied math1430
  • Hard prompts, English1430
  • Hard prompts1429
  • Math1428
  • Excluding ties1423
  • Polish1422
  • Business & finance1420
  • Non-English1417
  • French1417
  • Japanese1416
  • Multi-turn1415
  • Russian1413
  • Long prompts1412
  • German1407
  • Media & sports1405
  • Instructions1404
  • Writing & literature1402
  • Creative writing1395
  • Korean1379

Score by size

Plot against
Best for its size

About as strong, smaller

Compare

Built on it

Quantizations
26
Fine-tunes
7
Adapters
0
Merges
1

Ways to run it

Most downloaded

BenchClub runs

Not runnable yet

Runs open once a GLM-4.5 build is registered.

More from Z.ai

See more

Other >300B models

See more