Qwen 3 30b A3B is a 30b model with 3 billion active parameters per pass. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.
Added Feb 27, 2025
Context Window
41.0K
Max Output
32.8K
Input Price (Auto)
$0.10/1M
Output Price (Auto)
$0.30/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
12.5
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
13.3
GPQA Diamond
Graduate-level scientific reasoning
51.5%
Better than 35% of models compared
HLE
Humanity's Last Exam
4.6%
Better than 31% of models compared
IFBench
Instruction-following benchmark
31.9%
Better than 23% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
22.2%
Better than 28% of models compared
AA-LCR
Long context reasoning evaluation
0.0%
Better than 7% of models compared
SciCode
Python programming for scientific computing
26.4%
Better than 39% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
6.8%
Better than 43% of models compared
AIME 2025
American Invitational Mathematics Examination 2025
21.7%
Better than 23% of models compared
AIME
American Invitational Mathematics Examination
26.0%
Better than 53% of models compared
MMLU-Pro
Professional and academic subject knowledge
71.0%
Better than 38% of models compared
Last updated May 15, 2026
Artificial AnalysisLiveCodeBench
Contamination-free coding benchmark
32.2%
Better than 39% of models compared
Math-500
Diverse mathematical problem solving benchmark
86.3%
Better than 55% of models compared
