NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Qwen3 30B A3B Instruct 2507
Alibaba Qwen logo

Qwen3 30B A3B Instruct 2507

by Alibaba Qwen · Released Jul 2025

Open Source
40.1
avg score
Rank #209
Compare
Better than 36% of all models
Context
262K tokens (~131 books)
Input $/1M
$0.10
Output $/1M
$0.30
Type
text
License
Open Source
Benchmarks
7 tested
Data as of
About

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

Tested on 7 benchmarks · BenchGecko score 40.1. Top scores: Chatbot Arena Elo · Overall (1382.7%), OpenCompass · IFEval (83.9%), OpenCompass · MMLU-Pro (73.9%).

Looking for similar performance at lower cost?
ERNIE 4.5 21B A3B Thinking scores 39.8 (99% as good) at $0.07/1M input · 30% cheaper
Capabilities
coding
38.7
#147 globally
math
63.8
#83 globally
knowledge
48.4
#150 globally
language
83.9
#42 globally
Benchmark Scores
Compare All
Tested on 7 benchmarks · Ranked across 5 categories
Score Distribution (all 327 models)
0255075100
▲ You are here
codingCompare coding →
OpenCompass · LiveCodeBenchV6

OpenCompass Live Code Bench v6. Fresh competitive programming problems to evaluate code generation without memorization.

38.7·
mathCompare math →
OpenCompass · AIME2025

OpenCompass evaluation on AIME 2025 problems. Tests mathematical reasoning on fresh competition problems.

63.8·
knowledgeCompare knowledge →
OpenCompass · MMLU-Pro

OpenCompass MMLU-Pro evaluation. Harder knowledge test with more answer choices.

73.9·
OpenCompass · GPQA-Diamond

OpenCompass evaluation of GPQA Diamond. PhD-level science questions from the hardest subset.

63.6·
OpenCompass · HLE

OpenCompass evaluation of Humanitys Last Exam. Expert-level cross-discipline knowledge test.

7.7·
Quick compare:vs Yi 6Bbaidu logovs ERNIE 4.5 21B A3B ThinkingGoogle DeepMind logovs Gemini 1.5 Pro (Feb 2024)
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · Alibaba Qwen Qwen 3
Apr 2025
38.9
$0.10/M in41Kctx6 benchmarks
Apr 2025
54.3+15.4
$0.46/M in(+0.35)131Kctx(+90K)10 benchmarks
Jul 2025
44.8-9.5
$0.14/M in(-0.32)262Kctx(+131K)22 benchmarks
Jul 2025
54.6+9.8
$0.45/M in(+0.31)128Kctx(-134K)27 benchmarks
Apr 2025
33.8-20.8
$0.12/M in(-0.33)41Kctx(-87K)9 benchmarks
Jul 2025
40.1+6.3
$0.10/M in(-0.02)262Kctx(+221K)7 benchmarks
Aug 2025
63.5+23.4
$0.20/M in(+0.10)82Kctx(-180K)6 benchmarks
Apr 2025
47.6-15.9
$0.08/M in(-0.12)131Kctx(+49K)14 benchmarks
Apr 2025
$0.00/M in(-0.08)41Kctx(-90K)
Apr 2025
36.1-11.5
$0.12/M in(+0.12)131Kctx(+90K)12 benchmarks
Jul 2025
$0.15/M in(+0.03)262Kctx(+131K)
Jul 2025
$0.30/M in(+0.15)262Kctx
Jul 2025
$0.00/M in(-0.30)1.0Mctx(+786K)3 benchmarks
Sep 2025
$0.20/M in(+0.20)1.0Mctx(-49K)
Feb 2026
$0.12/M in(-0.08)262Kctx(-738K)12 benchmarks
Sep 2025
$0.65/M in(+0.53)1.0Mctx(+738K)
Sep 2025
47.4+11.3
$0.78/M in(+0.13)262Kctx(-738K)13 benchmarks
Feb 2026
$0.78/M in262Kctx3 benchmarks
Sep 2025
49.2+1.8
$0.09/M in(-0.69)262Kctx26 benchmarks
Sep 2025
$0.00/M in(-0.09)262Kctx3 benchmarks
Sep 2025
56.8+7.6
$0.15/M in(+0.15)262Kctx20 benchmarks
Sep 2025
$0.21/M in(+0.06)262Kctx1 benchmark
Sep 2025
$0.40/M in(+0.19)131Kctx(-131K)1 benchmark
Oct 2025
$0.15/M in(-0.25)262Kctx(+131K)
Oct 2025
$0.29/M in(+0.14)262Kctx
Oct 2025
$0.10/M in(-0.19)131Kctx(-131K)
Oct 2025
$0.25/M in(+0.15)262Kctx(+131K)
Oct 2025
$0.18/M in(-0.07)131Kctx(-131K)
See the full Qwen 3 family →
Recently Happened
Qwen3 30B A3B Instruct 2507 pricing increased 11%
Oct 29, 2026
Qwen3 30B A3B Instruct 2507 pricing dropped 10%
Oct 19, 2026
Qwen3 30B A3B Instruct 2507 pricing dropped 47%
Sep 13, 2026
Qwen3 30B A3B Instruct 2507 pricing increased 87%
Sep 10, 2026
Similar Models
Yi 6B
Unknown
40.4n/a
baidu logo
ERNIE 4.5 21B A3B Thinking
baidu
39.8$0.07/1M
Google DeepMind logo
Gemini 1.5 Pro (Feb 2024)
Google DeepMind
40.8n/a
Links
Info
Alibaba QwenPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Alibaba Qwen
Source Code
GitHubHugging Face
BenchGecko API
qwen3-30b-a3b-instruct-2507
Specifications
  • Typetext
  • Context262K tokens (~131 books)
  • ReleasedJul 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.001
Available On
Alibaba Qwen logoAlibaba Qwen$0.10
Categories
codingmathknowledgelanguage
Learn More
context-windowtransformeropen weightstokens
Share & Export
Tweet
Related Models
Yi 6B
40.4
baidu logoERNIE 4.5 21B A3B Thinking
39.8
Google DeepMind logoGemini 1.5 Pro (Feb 2024)
40.8
Anthropic logoClaude 3.5 Sonnet
39.4
Qwen3 30B A3B Instruct 2507 is an open-source text AI model by Alibaba Qwen, released in July 2025. It has an average benchmark score of 40.1. Context window: 262K tokens.

Related Models

Yi 6B · UnknownERNIE 4.5 21B A3B Thinking · baiduGemini 1.5 Pro (Feb 2024) · Google DeepMindClaude 3.5 Sonnet · AnthropicQwen3.5-9B · Alibaba Qwen

Benchmarks

Chatbot Arena Elo · OverallOpenCompass · IFEvalOpenCompass · MMLU-ProOpenCompass · AIME2025OpenCompass · GPQA-Diamond

Related Pages

Alibaba Qwen · ProviderAlibaba Qwen · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-11-12

  • Qwen3 30B A3B Instruct 2507 by Alibaba Qwen. BenchGecko score 40.1, rank 209 of 327 scored models (normalized average of public benchmark scores).
  • List price $0.10 input · $0.30 output per 1M tokens (as of 2026-11-12).
  • Sold by 3 providers (as of 2026-11-12): DekaLLM $0.0900 in / $0.30 out · SiliconFlow (fp8) $0.0900 in / $0.30 out · Nebius (fp8) $0.10 in / $0.30 out. Every provider

How to cite · data as of 2026-11-12

Qwen3 30B A3B Instruct 2507 · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-12. https://benchgecko.ai/model/qwen3-30b-a3b-instruct-2507

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP