Qwen3-30B-A3B-Instruct-2507

Qwen
$ uv tool install "git+https://github.com/holaboss-ai/holaOS@feat/benchclub-cli#subdirectory=packages/benchclub"
$ benchclub login && benchclub run qwen3:30b-a3b-instruct-2507-q4_K_M

BenchClub cloud

No cloud result yet

Headline numbers come from BenchClub’s pinned cloud runner.

Arena score
1384
Among open models
#53of 148
Among all on Arena
#175
Votes
23,286

Measured on Qwen3-30B-A3B-Instruct (2507), the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.

Score by category

CategoryScore
  • Chinese1433
  • French1418
  • Software & IT1417
  • Coding1416
  • Applied math1412
  • Hard prompts, English1406
  • Spanish1404
  • Hard prompts1398
  • Expert1396
  • Math1395
  • Science1393
  • Medicine & health1392
  • English1391
  • Business & finance1389
  • Legal & government1387
  • German1379
  • Long prompts1379
  • Multi-turn1378
  • Non-English1372
  • Russian1369
  • Instructions1363
  • Excluding ties1358
  • Polish1353
  • Japanese1338
  • Writing & literature1336
  • Media & sports1334
  • Korean1331
  • Creative writing1317

Score by size

Plot against
Best for its size
ModelParamsScore
Qwen3-0.6B752M—
Qwen3-1.7B2.0B—
Qwen3-4B4.0B—
Qwen3-4B-Instruct-25074.0B—
Qwen3-8B8.2B—
Qwen3-14B14.8B—
Qwen3-30B-A3B30.5B1317
Qwen3-30B-A3B-Instruct-250730.5B1384
Qwen3-32B32.8B1340
Qwen3-235B-A22B235B1394
Qwen3-235B-A22B-Instruct-2507235B1419

BenchClub runs

No runs yet

Be the first to benchmark Qwen3-30B-A3B-Instruct-2507 on your own hardware.

Discussion

Built on it

Quantizations
148
Fine-tunes
126
Adapters
86
Merges
12

Ways to run it

Most downloaded

More from Qwen

See more

Other 20–40B models

See more