Qwen3 30B A3B 2507 (Reasoning)
AlibabaQwenOpen WeightApache 2.0 · Commercial OK
Description
Qwen3-30B-A3B is a smaller Mixture-of-Experts (MoE) model from the Qwen3 series by Alibaba, with 30.5 billion total parameters and 3.3 billion activated parameters. Features hybrid thinking/non-thinking modes, support for 119 languages, and enhanced agent capabilities. It aims to outperform previous models like QwQ-32B while using significantly fewer activated parameters.
Release Date
2025-07-30
Parameters
30.5B
Context Length
41K
Modalities
text
Capability Radar
70
general
60
coding
80
reasoning
60
scienceest.
70
agents
0
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
No ranking data available
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Chat
Multi-IF
72.2%SR
General
Arena Hard
91.0%SR
BFCL
69.1%SR
Math
AIME 2024
80.4%SR
LiveBench
74.3%SR
AIME 2025
70.9%SR
Reasoning
GPQANYU + Cohere + Anthropic (2023)
65.8%SR
LiveCodeBench
62.6%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Creativity90
Writing90
Chat80
Math80
Instruction Following70
Language70
Physics70
Reasoning70
Structured Output70
General70
Biology70
Chemistry70
Communication70
Tool Calling70
Code60
Pricing
Input Price$0.1 / 1M tokens
Output Price$0.44 / 1M tokens
Blended Price (3:1)$0.185 / 1M tokens
Speed
No speed data available
Provider Price Ranking
Provider Price Ranking
4 providers
Cheapest: AlibabaMost Expensive: Fireworks
ProviderInputOutput
1AlibabaPRIMARY
$0.1
$0.44
2Novita
$0.1
$0.44
3DeepInfra
$0.12
$0.5
4Fireworks
$0.89
$0.89
Compare pricing across different API providers for this model.