Qwen3 30B A3B 2507 (Reasoning)
Jul 2025
Qwen3 30B A3B 2507 (Reasoning)Compare inon
Benchmarks of Qwen3 30B A3B 2507 (Reasoning)29
BenchmarkByScoreRank
Overall1
Knowledge4
Science3
Coding3
Agents4
Documents2
Legacy · saturated or no longer reported12
No benchmark matches
$0.066per task?
price not verifiedprice
—output speed?
262Kcontext
Rankingin thinking mode?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperMiMo v2.6 FlashthinkingOpen×3.9-5%$0.062Memory (4-bit): 18 GB → 186 GB+4
BetterGPT-6 Lunalow×2.2-93%$0.005Function calling only with none · Chat Completions+3OpenQwen3.8 27Bxhigh×3.4+1,428%$1.01max_tokens range · QwenCloud+4
CheaperClaude Haiku 5.5medium×3.5-29%$0.047Remove sampling parameters+5CheaperGPT-5.6 Lunahigh×3.3-33%$0.044ModelScoreCostPer taskWhat changes
MiMo v2.6 FlashthinkingOpen×3.9-5%$0.062Memory (4-bit): 18 GB → 186 GB+4GPT-6 Lunaxhigh×3.5-36%$0.042Function calling only with none · Chat Completions+3Claude Haiku 5.5medium×3.5-29%$0.047Remove sampling parameters+5GPT-5.6 Lunahigh×3.3-33%$0.044MiMo v2.5 ProthinkingOpen×2.7-18%$0.054Memory (4-bit): 18 GB → 614 GBModelScoreCostPer taskWhat changes
GPT-6 Lunalow×2.2-93%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow×2.1-85%$0.01MiMo v2.5thinkingOpen×2.2-71%$0.019Memory (4-bit): 18 GB → 186 GBClaude Haiku 5.5low×3-63%$0.024Remove sampling parameters+5GPT-5 Minihigh+71%-19%$0.053ModelScoreCostPer taskWhat changes
Qwen3.8 27BxhighOpen×3.4+1,428%$1.01max_tokens range · QwenCloud+4IK2 Horizon MoVA 36B A4BthinkingOpen×2.6—$1 / $4Memory (4-bit): 18 GB → 22 GBQwen 3.5 27BthinkingOpen×2.3—$0.30 / $2.40AG9v3 39A5BOpen×2.2——Context: 262K → 131K+1Qwen3.6 27BthinkingOpen×2.2+842%$0.62ModelScoreCostPer taskWhat changes
Qwen3.8 Max (0902)thinking×4.6+8,101%$5.41Qwen3.8 2.4T A95BthinkingOpen×4.1+3,168%$2.16Memory (4-bit): 18 GB → 1,468 GB+5Qwen3.8 FlashthinkingOpen×4.1+464%$0.37Memory (4-bit): 18 GB → 108 GB+6Qwen3.7 Maxthinking×3+1,640%$1.15Qwen3.6 Max Previewthinking×2.9—$1.30 / $7.80Include the word JSON · QwenCloudQwen3.8 27BmediumOpen×2.8+1,618%$1.13max_tokens range · QwenCloud+4Qwen3.6 Plusthinking×2.8—$0.50 / $3Qwen3.7 Plusthinking×2.6+229%$0.22All Alibaba (Qwen) models →Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✗ 16 GB✓ 24 GB GPU · compressed✓ 48 GB GPU · 8-bit✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
History
2 versionsBenchmarks
all categoriesChat & Knowledge
Humanity's Last Exam10.3#187
AA Omniscience Index-56.1#242
CritPt (physics)0.3#149
AA Intelligence Index 4.3.29.8#211
AA Omniscience · Accuracy16.3#215
AA-LCR (long context) 1.161.3#153
GDP.pdf · AA all-pass0.4#128
MMLU-Pro · official boardlab80.9
GPQA Diamond70.7#182
AIME 2025 · AA archived56.3#84
Coding
SciCode33#118
Terminal-Bench 2.11.5#148
LiveCodeBench · AA archived70.7#44
Agents & Tool Use
AutomationBench-AA0.8#114
τ³-Banking · AA5.4#116
AA-Briefcase 1.1 · Elo5.3#128
τ²-bench · AA28.1#154
Writing & Language
IFBench (instructions)50.7#114
FAQ
How much does Qwen3 30B A3B 2507 (Reasoning) cost?›
There is no per-unit API price: price not verified.
How good is Qwen3 30B A3B 2507 (Reasoning), and what is it best at?›
#186 of 334 in Chat & Knowledge, #75 of 132 in Coding, #114 of 133 in Agents & Tool Use, #113 of 245 in Writing & Language, #128 of 133 in Vision & Documents.
Is Qwen3 30B A3B 2507 (Reasoning) better than Qwen3 14B?›
On AA Intelligence Index 4.3.2, Qwen3 30B A3B 2507 (Reasoning) scores 9.8 vs 6.7 — higher.
What is the context window of Qwen3 30B A3B 2507 (Reasoning)?›
262K tokens.
When was Qwen3 30B A3B 2507 (Reasoning) released? Is there a newer version?›
Released 2025-07-30. It has been superseded by Qwen 3.5 35B A3B.
Is Qwen3 30B A3B 2507 (Reasoning) open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Qwen3 30B A3B 2507 (Reasoning) locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Qwen3 30B A3B 2507 (Reasoning) read images?›
No, it accepts text only.
What is Qwen3 30B A3B 2507 (Reasoning)?›
Qwen3 30B A3B 2507 (Reasoning) is an open-weights language model from Alibaba (Qwen), released Jul 2025, the successor to Qwen3 14B.
What are the best alternatives to Qwen3 30B A3B 2507 (Reasoning)?›
MiMo v2.6 Flash (cheaper), GPT-6 Luna (better), Qwen3.8 27B (open weights).