Mistral-Large-3-675B-Instruct-2512

Mistral AI
Arena score
1429
Among open models
#24of 148
Among all on Arena
#98
Votes
88,567

Measured on Mistral Large 3, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.

Score by category

CategoryScore
  • French1455
  • Software & IT1451
  • Coding1449
  • Medicine & health1447
  • Science1446
  • Chinese1446
  • Polish1441
  • Legal & government1441
  • English1440
  • German1439
  • Hard prompts, English1437
  • Spanish1436
  • Hard prompts1431
  • Multi-turn1429
  • Applied math1425
  • Expert1422
  • Excluding ties1421
  • Business & finance1418
  • Math1416
  • Long prompts1415
  • Non-English1414
  • Russian1412
  • Instructions1405
  • Writing & literature1397
  • Japanese1397
  • Korean1390
  • Media & sports1387
  • Creative writing1386

Score by size

Plot against
Best for its size

About as strong, smaller

Compare

Built on it

Quantizations
7
Fine-tunes
0
Adapters
0
Merges
1

Ways to run it

Most downloaded

BenchClub runs

Not runnable yet

Runs open once a Mistral-Large-3-675B-Instruct-2512 build is registered.

More from Mistral AI

See more

Other >300B models

See more