Noometry

Alibaba (Qwen), open weights

Qwen3-30B-A3B

Qwen3-30B-A3B by Alibaba (Qwen) ranks 179th of 354 ranked models on the Noometry Index as of October 2026, with a score of 38.9. Its strongest category is agentic & tool use, where it ranks 82nd. API pricing starts at $0.12 per million input tokens and $0.50 per million output tokens, with a 41K-token context window.

Last verified

Noometry rank
#179 of 354
Index score
38.9
Evidence
Confirmed 32 results
Provider
Alibaba (Qwen)
Released
April 28, 2025
Weights
Open weights
Reasoning
Yes
Context window
41K
Max output
16K
Input price
$0.12 / M
Output price
$0.50 / M
Blended price
$0.21 / M
Output speed
42 tokens/s Kagi
Value
#46 of 219
Knowledge cutoff
Unknown
Input
text
Hugging Face
Qwen/Qwen3-30B-A3B

Category scores

Each category score combines every public result we have in that category.

  1. Coding 37.5
  2. Agentic & Tool Use 29.8
  3. Reasoning 22.2
  4. Math 37.4
  5. Knowledge 41.8
  6. Multilingual 49.5
  7. Instruction Following 72.0
  8. Long Context 31.0
  9. Writing & Preference 55.6
CategoryScoreRankResults
Coding37.5#1943
Agentic & Tool Use29.8#821
Reasoning22.2#2046
Math37.4#1573
Knowledge41.8#1053
Multilingual49.5#1321
Instruction Following72.0#1421
Long Context31.0#2832
Writing & Preference55.6#1434

Strengths and weaknesses

Categories where Qwen3-30B-A3B places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Knowledge41.8+4.5#105 of 314, top 34%
Multilingual49.5+2.1#132 of 297, top 45%
Writing & Preference55.6+1.9#143 of 312, top 46%

Weakest categories

CategoryScorevs medianRank
Long Context31.0−9.9#283 of 296, top 96%
Reasoning22.2−1.4#204 of 350, top 59%
Coding37.5−1.2#194 of 340, top 58%

Closest competitors

The models ranked just above and below Qwen3-30B-A3B. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Mercury 2#17539.1$0.38—Compare
Mistral Large 3#17639.1$0.387Compare
GLM-4.5-Air#17738.9$0.43160Compare
MiniMax-M2.1#17838.9$0.52—Compare
GLM-4.7-Flash#18038.8$0.15—Compare
Qwen2.5 Plus 1127#18138.8——Compare
Qwen3.6 Flash#18238.8$0.42—Compare
Olmo 3 32b Think#18338.7——Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
SciCode33.3%#102 of 121, top 85%Epoch AI
WeirdML29.8%#97 of 119, top 82%Epoch AI
LMArena Coding1337LMArena2026-10-08
LMArena Coding1416#120 of 294, top 41%LMArena2026-10-08

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
Berkeley Function Calling Leaderboard41.4%#22 of 49, top 45%fcBerkeley Function Calling Leaderboard

Reasoning

BenchmarkScorePositionSettingSourceDate
Kagi LLM Benchmark54.9%#52 of 99, top 53%Kagi LLM Benchmark
CritPt0.3%#97 of 134, top 73%Epoch AI
Chess Puzzles8%#85 of 129, top 66%Epoch AI2026-08-30
Chess Puzzles4%Epoch AI2026-08-30
Chess Puzzles2%Epoch AI2026-08-30
Chess Puzzles1%noneEpoch AI2026-08-30
LMArena Hard Prompts1314LMArena2026-10-08
LMArena Hard Prompts1398#130 of 297, top 44%LMArena2026-10-08
DTBench67.2%Epoch AI
DTBench60.3%Epoch AI
DTBench69.3%#93 of 151, top 62%Epoch AI
LMCA22.4%#89 of 125, top 72%Epoch AI
LMCA19.5%Epoch AI
LMCA15.8%Epoch AI
Epoch Capabilities Index139.63#110 of 213, top 52%Epoch AI2025-07-30
Epoch Capabilities Index137.42Epoch AI2025-07-29
Epoch Capabilities Index136.18Epoch AI2025-04-29

Math

BenchmarkScorePositionSettingSourceDate
MathArena Final-Answer Competitions47.8%#28 of 29, top 97%MathArena
OTIS Mock AIME 2024-202562.8%Epoch AI2026-08-28
OTIS Mock AIME 2024-202570.3%#92 of 173, top 54%Epoch AI2026-08-30
OTIS Mock AIME 2024-202562.2%Epoch AI2026-08-30
OTIS Mock AIME 2024-202525.6%noneEpoch AI2026-08-30
LMArena Math1355LMArena2026-10-08
LMArena Math1394#133 of 285, top 47%LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond55.6%Epoch AI2026-08-30
GPQA Diamond61.7%Epoch AI2026-08-30
GPQA Diamond70.1%#98 of 186, top 53%Epoch AI2026-08-30
GPQA Diamond50.4%noneEpoch AI2026-08-30
Confabulations (lower is better)12.3%#6 of 51, top 12%Lech Mazur benchmarks
LMArena Expert1396#127 of 273, top 47%LMArena2026-10-08
LMArena Expert1314LMArena2026-10-08

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1372#132 of 297, top 45%LMArena2026-10-08
LMArena Non-English1295LMArena2026-10-08
LMArena Chinese1347LMArena2026-10-08
LMArena Chinese1433#116 of 285, top 41%LMArena2026-10-08
LMArena French1352LMArena2026-10-08
LMArena French1418#102 of 223, top 46%LMArena2026-10-08
LMArena German1380#111 of 231, top 49%LMArena2026-10-08
LMArena German1307LMArena2026-10-08
LMArena Japanese1254LMArena2026-10-08
LMArena Japanese1337#107 of 211, top 51%LMArena2026-10-08
LMArena Korean1331#113 of 213, top 54%LMArena2026-10-08
LMArena Korean1261LMArena2026-10-08
LMArena Russian1291LMArena2026-10-08
LMArena Russian1370#136 of 283, top 49%LMArena2026-10-08
LMArena Spanish1317LMArena2026-10-08
LMArena Spanish1404#107 of 226, top 48%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1363#137 of 298, top 46%LMArena2026-10-08
LMArena Instruction Following1283LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
Fiction.LiveBench40.6%#43 of 47, top 92%Epoch AI
LMArena Longer Query1379#133 of 291, top 46%LMArena2026-10-08
LMArena Longer Query1312LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1384#132 of 297, top 45%LMArena2026-10-08
LMArena Text1317LMArena2026-10-08
LMArena Creative Writing1271LMArena2026-10-08
LMArena Creative Writing1317#156 of 295, top 53%LMArena2026-10-08
Short-Story Creative Writing75.3%#24 of 39, top 62%Epoch AI
LMArena Multi-Turn1307LMArena2026-10-08
LMArena Multi-Turn1378#136 of 295, top 47%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
deepinfra$0.12$0.50—2026-10-10
openrouter$0.12$0.50—2026-10-10

All Alibaba (Qwen) API prices → Estimate your cost →

Compare Qwen3-30B-A3B

Other Alibaba (Qwen) models

Frequently asked questions

How good is Qwen3-30B-A3B?

Qwen3-30B-A3B by Alibaba (Qwen) ranks 179th of 354 ranked models on the Noometry Index as of October 2026, with a score of 38.9. Its strongest category is agentic & tool use, where it ranks 82nd. API pricing starts at $0.12 per million input tokens and $0.50 per million output tokens, with a 41K-token context window.

How much does Qwen3-30B-A3B cost?

Qwen3-30B-A3B costs $0.12 per million input tokens and $0.50 per million output tokens on deepinfra.

What is Qwen3-30B-A3B's context window?

Qwen3-30B-A3B accepts up to 41K tokens of input and can write up to 16K tokens in one response.

Is Qwen3-30B-A3B open source?

Yes. Qwen3-30B-A3B's weights are downloadable from Hugging Face (Qwen/Qwen3-30B-A3B); check the license for commercial terms.

How fast is Qwen3-30B-A3B?

Qwen3-30B-A3B generated about 42 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

What are Qwen3-30B-A3B's strengths and weaknesses?

Relative to other ranked models, Qwen3-30B-A3B places best in knowledge, multilingual, writing & preference and lowest in long context, reasoning, coding.

What is Qwen3-30B-A3B best at?

Its best category is agentic & tool use, where it ranks 82nd on Noometry.