Arena score
1475
Among open models
#2of 148
Among all on Arena
#28
Votes
41,402

Measured on Kimi K3 (Max), 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#1Applied math#1Science#1Legal & government#1Japanese

CategoryScore
  • Chinese1527
  • Expert1515
  • Applied math1507
  • Coding1506
  • Science1502
  • Legal & government1498
  • Software & IT1497
  • Math1496
  • Japanese1495
  • Hard prompts1494
  • Hard prompts, English1493
  • Long prompts1490
  • Multi-turn1489
  • Medicine & health1488
  • Instructions1484
  • German1483
  • French1482
  • Excluding ties1482
  • Russian1481
  • English1479
  • Spanish1477
  • Polish1472
  • Business & finance1469
  • Writing & literature1468
  • Non-English1465
  • Creative writing1453
  • Media & sports1450
  • Korean1444

Score by size

Plot against
Best for its size

About as strong, smaller

Compare

Discussion

Built on it

Quantizations
58
Fine-tunes
58
Adapters
7
Merges
0

Ways to run it

Most downloaded

BenchClub runs

Not runnable yet

Runs open once a Kimi-K3 build is registered.

More from Moonshot AI

See more

Other >300B models

See more