gpt-oss-120b

OpenAI
Arena score
1366
Among open models
#60of 148
Among all on Arena
#197
Votes
30,115

Measured on gpt-oss-120b, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.

Score by category

CategoryScore
  • Math1389
  • Spanish1388
  • Medicine & health1388
  • Software & IT1387
  • Applied math1387
  • Chinese1385
  • Science1382
  • Coding1380
  • English1375
  • French1369
  • Hard prompts, English1368
  • Hard prompts1363
  • Business & finance1359
  • Expert1355
  • Legal & government1355
  • German1354
  • Polish1353
  • Non-English1350
  • Russian1343
  • Multi-turn1340
  • Japanese1331
  • Excluding ties1330
  • Long prompts1319
  • Instructions1318
  • Writing & literature1305
  • Media & sports1292
  • Korean1282
  • Creative writing1274

Score by size

Plot against
Best for its size

About as strong, smaller

Compare

Built on it

Quantizations
137
Fine-tunes
127
Adapters
324
Merges
1

Ways to run it

Most downloaded

BenchClub runs

Not runnable yet

Runs open once a gpt-oss-120b build is registered.

More from OpenAI

See more

Other 80–300B models

See more