Kimi-K2.6

Moonshot AI
Arena score
1455
Among open models
#9of 148
Among all on Arena
#47
Votes
39,551

Measured on Kimi K2.6, 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#5Chinese#6Expert#6Coding#6Korean

CategoryScore
  • Chinese1521
  • Expert1492
  • Coding1489
  • Software & IT1484
  • Applied math1480
  • Math1475
  • French1471
  • Hard prompts, English1471
  • Hard prompts1470
  • Long prompts1468
  • Science1468
  • Spanish1464
  • Legal & government1461
  • English1460
  • Medicine & health1456
  • Excluding ties1455
  • German1454
  • Multi-turn1454
  • Instructions1451
  • Non-English1446
  • Russian1446
  • Business & finance1445
  • Japanese1440
  • Writing & literature1439
  • Polish1438
  • Creative writing1433
  • Media & sports1428
  • Korean1427

Score by size

Plot against
Best for its size

About as strong, smaller

Compare

Discussion

Built on it

Quantizations
45
Fine-tunes
18
Adapters
14
Merges
1

Ways to run it

Most downloaded

BenchClub runs

Not runnable yet

Runs open once a Kimi-K2.6 build is registered.

More from Moonshot AI

See more

Other >300B models

See more