Model profile · Qwen

Qwen3 30B A3B

Open weightsbudget · registry tag 2026 open efficient

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 0.7%
Verified coverage: 0.7%
Spread: n/a
Last verified: Jun 20, 2026

48%bench fit

textcode2 aliases28 official source links

Open compare

Data version

Current snapshot.

Data version Jun 20, 2026Model list checked9 providers · 1081 tracked modelsPage refreshed Jul 5, 2026

The registry snapshot and page stamp are shown so a stale deploy is visible at a glance.

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set.

Thin verified coverageThis model currently reads as thin verified coverage across the resolved source data.

Chat / text18 benchmarks48.9%

Text Arena

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #170

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,327
Percentile: 48%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: overall. Source rank: #203. Votes: 26486. Organization: alibaba. License: Apache 2.0.

48% percentile inside its fair comparison set

1,327Raw benchmark valueCI 1,323 - 1,332

Text Arena · Creative Writing

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #181

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,284
Percentile: 44.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: creative_writing. Source rank: #215. Votes: 3364. Organization: alibaba. License: Apache 2.0.

44.3% percentile inside its fair comparison set

1,284Raw benchmark valueCI 1,274 - 1,295

Text Arena · English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #169

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,346
Percentile: 48.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: english. Source rank: #201. Votes: 13391. Organization: alibaba. License: Apache 2.0.

48.3% percentile inside its fair comparison set

1,346Raw benchmark valueCI 1,340 - 1,352

Text Arena · Exclude Ties

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #170

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,276
Percentile: 48%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: exclude_ties. Source rank: #203. Votes: 18351. Organization: alibaba. License: Apache 2.0.

48% percentile inside its fair comparison set

1,276Raw benchmark valueCI 1,269 - 1,283

Text Arena · Hard Prompts

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #162

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,345
Percentile: 50.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: hard_prompts. Source rank: #193. Votes: 10694. Organization: alibaba. License: Apache 2.0.

50.5% percentile inside its fair comparison set

1,345Raw benchmark valueCI 1,339 - 1,352

Text Arena · Hard Prompts English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #159

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,363
Percentile: 51.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: hard_prompts_english. Source rank: #190. Votes: 5811. Organization: alibaba. License: Apache 2.0.

51.2% percentile inside its fair comparison set

1,363Raw benchmark valueCI 1,354 - 1,371

Text Arena · Instruction Following

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #174

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,312
Percentile: 46.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: instruction_following. Source rank: #207. Votes: 6129. Organization: alibaba. License: Apache 2.0.

46.8% percentile inside its fair comparison set

1,312Raw benchmark valueCI 1,304 - 1,320

Text Arena · Longer Query

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #158

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,340
Percentile: 48.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: longer_query. Source rank: #189. Votes: 4458. Organization: alibaba. License: Apache 2.0.

48.4% percentile inside its fair comparison set

1,340Raw benchmark valueCI 1,331 - 1,349

Text Arena · Multi Turn

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #172

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,321
Percentile: 47.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: multi_turn. Source rank: #205. Votes: 4522. Organization: alibaba. License: Apache 2.0.

47.1% percentile inside its fair comparison set

1,321Raw benchmark valueCI 1,311 - 1,330

Text Arena · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #162

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,317
Percentile: 50.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: overall. Source rank: #191. Votes: 26486. Organization: alibaba. License: Apache 2.0.

50.5% percentile inside its fair comparison set

1,317Raw benchmark valueCI 1,312 - 1,322

Text Arena · Creative Writing · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #169

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,272
Percentile: 48%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: creative_writing. Source rank: #201. Votes: 3364. Organization: alibaba. License: Apache 2.0.

48% percentile inside its fair comparison set

1,272Raw benchmark valueCI 1,262 - 1,283

Text Arena · English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #163

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,335
Percentile: 50.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: english. Source rank: #190. Votes: 13391. Organization: alibaba. License: Apache 2.0.

50.2% percentile inside its fair comparison set

1,335Raw benchmark valueCI 1,329 - 1,341

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #163

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,261
Percentile: 50.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: exclude_ties. Source rank: #192. Votes: 18351. Organization: alibaba. License: Apache 2.0.

50.2% percentile inside its fair comparison set

1,261Raw benchmark valueCI 1,254 - 1,267

Text Arena · Hard Prompts · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #159

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 51.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: hard_prompts. Source rank: #188. Votes: 10694. Organization: alibaba. License: Apache 2.0.

51.4% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,309 - 1,322

Text Arena · Hard Prompts English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #160

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,331
Percentile: 50.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: hard_prompts_english. Source rank: #189. Votes: 5811. Organization: alibaba. License: Apache 2.0.

50.9% percentile inside its fair comparison set

1,331Raw benchmark valueCI 1,323 - 1,339

Text Arena · Instruction Following · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #166

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,286
Percentile: 49.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: instruction_following. Source rank: #196. Votes: 6129. Organization: alibaba. License: Apache 2.0.

49.2% percentile inside its fair comparison set

1,286Raw benchmark valueCI 1,278 - 1,293

Text Arena · Longer Query · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #158

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,313
Percentile: 48.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: longer_query. Source rank: #187. Votes: 4458. Organization: alibaba. License: Apache 2.0.

48.4% percentile inside its fair comparison set

1,313Raw benchmark valueCI 1,304 - 1,322

Text Arena · Multi Turn · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #163

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,308
Percentile: 49.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: multi_turn. Source rank: #193. Votes: 4522. Organization: alibaba. License: Apache 2.0.

49.8% percentile inside its fair comparison set

1,308Raw benchmark valueCI 1,299 - 1,317

Coding2 benchmarks52.5%

Text Arena · Coding

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #152

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,387
Percentile: 52.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: coding. Source rank: #180. Votes: 4527. Organization: alibaba. License: Apache 2.0.

52.8% percentile inside its fair comparison set

1,387Raw benchmark valueCI 1,378 - 1,396

Text Arena · Coding · No Style Control

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #154

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,338
Percentile: 52.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: coding. Source rank: #184. Votes: 4527. Organization: alibaba. License: Apache 2.0.

52.2% percentile inside its fair comparison set

1,338Raw benchmark valueCI 1,329 - 1,347

Reasoning / math / science2 benchmarks55.7%

Text Arena · Math

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #142

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,353
Percentile: 55.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: math. Source rank: #171. Votes: 1707. Organization: alibaba. License: Apache 2.0.

55.1% percentile inside its fair comparison set

1,353Raw benchmark valueCI 1,339 - 1,366

Text Arena · Math · No Style Control

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #138

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,355
Percentile: 56.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: math. Source rank: #166. Votes: 1707. Organization: alibaba. License: Apache 2.0.

56.4% percentile inside its fair comparison set

1,355Raw benchmark valueCI 1,341 - 1,368

Professional reasoning18 benchmarks48%

Text Arena · Expert

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #147

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,344
Percentile: 46.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: expert. Source rank: #177. Votes: 1316. Organization: alibaba. License: Apache 2.0.

46.9% percentile inside its fair comparison set

1,344Raw benchmark valueCI 1,327 - 1,360

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #160

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,330
Percentile: 50%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_business_and_management_and_financial_operations. Source rank: #189. Votes: 4013. Organization: alibaba. License: Apache 2.0.

50% percentile inside its fair comparison set

1,330Raw benchmark valueCI 1,320 - 1,339

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #191

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,271
Percentile: 41.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_entertainment_and_sports_and_media. Source rank: #227. Votes: 4574. Organization: alibaba. License: Apache 2.0.

41.2% percentile inside its fair comparison set

1,271Raw benchmark valueCI 1,262 - 1,280

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #196

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,323
Percentile: 34.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_legal_and_government. Source rank: #231. Votes: 1769. Organization: alibaba. License: Apache 2.0.

34.6% percentile inside its fair comparison set

1,323Raw benchmark valueCI 1,309 - 1,336

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #181

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,333
Percentile: 44.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_life_and_physical_and_social_science. Source rank: #214. Votes: 4610. Organization: alibaba. License: Apache 2.0.

44.3% percentile inside its fair comparison set

1,333Raw benchmark valueCI 1,324 - 1,342

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #131

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,368
Percentile: 57.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_mathematical. Source rank: #158. Votes: 1579. Organization: alibaba. License: Apache 2.0.

57.8% percentile inside its fair comparison set

1,368Raw benchmark valueCI 1,353 - 1,382

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #172

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,336
Percentile: 42%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_medicine_and_healthcare. Source rank: #205. Votes: 1620. Organization: alibaba. License: Apache 2.0.

42% percentile inside its fair comparison set

1,336Raw benchmark valueCI 1,321 - 1,351

Text Arena · Industry Software And It Services

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #158

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,372
Percentile: 51.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_software_and_it_services. Source rank: #189. Votes: 8311. Organization: alibaba. License: Apache 2.0.

51.7% percentile inside its fair comparison set

1,372Raw benchmark valueCI 1,365 - 1,378

Text Arena · Industry Writing And Literature And Language

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #174

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,305
Percentile: 46.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_writing_and_literature_and_language. Source rank: #208. Votes: 5967. Organization: alibaba. License: Apache 2.0.

46.6% percentile inside its fair comparison set

1,305Raw benchmark valueCI 1,297 - 1,313

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #146

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,314
Percentile: 47.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: expert. Source rank: #175. Votes: 1316. Organization: alibaba. License: Apache 2.0.

47.3% percentile inside its fair comparison set

1,314Raw benchmark valueCI 1,298 - 1,330

Text Arena · Industry Business And Management And Financial Operations · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #157

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,309
Percentile: 50.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_business_and_management_and_financial_operations. Source rank: #185. Votes: 4013. Organization: alibaba. License: Apache 2.0.

50.9% percentile inside its fair comparison set

1,309Raw benchmark valueCI 1,299 - 1,318

Text Arena · Industry Entertainment And Sports And Media · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #171

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,259
Percentile: 47.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_entertainment_and_sports_and_media. Source rank: #203. Votes: 4574. Organization: alibaba. License: Apache 2.0.

47.4% percentile inside its fair comparison set

1,259Raw benchmark valueCI 1,250 - 1,268

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #162

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,314
Percentile: 46%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_legal_and_government. Source rank: #189. Votes: 1769. Organization: alibaba. License: Apache 2.0.

46% percentile inside its fair comparison set

1,314Raw benchmark valueCI 1,300 - 1,327

Text Arena · Industry Life And Physical And Social Science · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #162

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,321
Percentile: 50.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_life_and_physical_and_social_science. Source rank: #189. Votes: 4610. Organization: alibaba. License: Apache 2.0.

50.2% percentile inside its fair comparison set

1,321Raw benchmark valueCI 1,312 - 1,330

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #129

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 58.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_mathematical. Source rank: #155. Votes: 1579. Organization: alibaba. License: Apache 2.0.

58.4% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,350 - 1,379

Text Arena · Industry Medicine And Healthcare · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #157

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,317
Percentile: 47.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_medicine_and_healthcare. Source rank: #185. Votes: 1620. Organization: alibaba. License: Apache 2.0.

47.1% percentile inside its fair comparison set

1,317Raw benchmark valueCI 1,302 - 1,332

Text Arena · Industry Software And It Services · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #155

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,340
Percentile: 52.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_software_and_it_services. Source rank: #184. Votes: 8311. Organization: alibaba. License: Apache 2.0.

52.6% percentile inside its fair comparison set

1,340Raw benchmark valueCI 1,334 - 1,347

Text Arena · Industry Writing And Literature And Language · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #165

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,291
Percentile: 49.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: industry_writing_and_literature_and_language. Source rank: #195. Votes: 5967. Organization: alibaba. License: Apache 2.0.

49.4% percentile inside its fair comparison set

1,291Raw benchmark valueCI 1,283 - 1,299

Multilingual14 benchmarks42.4%

Text Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #140

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,371
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: chinese. Source rank: #169. Votes: 1253. Organization: alibaba. License: Apache 2.0.

52.9% percentile inside its fair comparison set

1,371Raw benchmark valueCI 1,354 - 1,388

Text Arena · French

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #130

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 40.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: french. Source rank: #154. Votes: 322. Organization: alibaba. License: Apache 2.0.

40.3% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,334 - 1,398

Text Arena · German

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #146

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,303
Percentile: 38.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: german. Source rank: #176. Votes: 728. Organization: alibaba. License: Apache 2.0.

38.8% percentile inside its fair comparison set

1,303Raw benchmark valueCI 1,281 - 1,325

Text Arena · Japanese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #127

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,251
Percentile: 37.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: japanese. Source rank: #156. Votes: 665. Organization: alibaba. License: Apache 2.0.

37.9% percentile inside its fair comparison set

1,251Raw benchmark valueCI 1,228 - 1,275

Text Arena · Korean

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #135

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,267
Percentile: 35.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: korean. Source rank: #167. Votes: 440. Organization: alibaba. License: Apache 2.0.

35.6% percentile inside its fair comparison set

1,267Raw benchmark valueCI 1,239 - 1,296

Text Arena · Russian

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #171

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,307
Percentile: 41.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: russian. Source rank: #205. Votes: 1908. Organization: alibaba. License: Apache 2.0.

41.2% percentile inside its fair comparison set

1,307Raw benchmark valueCI 1,294 - 1,320

Text Arena · Spanish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #139

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,324
Percentile: 35.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: spanish. Source rank: #171. Votes: 410. Organization: alibaba. License: Apache 2.0.

35.5% percentile inside its fair comparison set

1,324Raw benchmark valueCI 1,294 - 1,354

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #135

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,356
Percentile: 54.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: chinese. Source rank: #161. Votes: 1253. Organization: alibaba. License: Apache 2.0.

54.6% percentile inside its fair comparison set

1,356Raw benchmark valueCI 1,339 - 1,372

Text Arena · French · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #122

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,355
Percentile: 44%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: french. Source rank: #145. Votes: 322. Organization: alibaba. License: Apache 2.0.

44% percentile inside its fair comparison set

1,355Raw benchmark valueCI 1,323 - 1,387

Text Arena · German · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #131

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,308
Percentile: 45.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: german. Source rank: #156. Votes: 728. Organization: alibaba. License: Apache 2.0.

45.1% percentile inside its fair comparison set

1,308Raw benchmark valueCI 1,287 - 1,330

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #115

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,252
Percentile: 43.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: japanese. Source rank: #140. Votes: 665. Organization: alibaba. License: Apache 2.0.

43.8% percentile inside its fair comparison set

1,252Raw benchmark valueCI 1,229 - 1,275

Text Arena · Korean · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #127

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,262
Percentile: 39.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: korean. Source rank: #153. Votes: 440. Organization: alibaba. License: Apache 2.0.

39.4% percentile inside its fair comparison set

1,262Raw benchmark valueCI 1,233 - 1,290

Text Arena · Russian · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #161

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,289
Percentile: 44.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: russian. Source rank: #191. Votes: 1908. Organization: alibaba. License: Apache 2.0.

44.6% percentile inside its fair comparison set

1,289Raw benchmark valueCI 1,276 - 1,302

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #131

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,318
Percentile: 39.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `qwen3-30b-a3b`. Category: spanish. Source rank: #158. Votes: 410. Organization: alibaba. License: Apache 2.0.

39.3% percentile inside its fair comparison set

1,318Raw benchmark valueCI 1,288 - 1,348

Source links and registry checks

official

Qwen3 announcement

Jun 20, 2026

Qwen3 30B A3B

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

Qwen3 30B A3B

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks