Private AI
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.
Added Feb 20, 2025
Model weightsContext Window
256.0K
Max Output
32.8K
Input Price (Auto)
$0.20/1M
Output Price (Auto)
$0.50/1M
Cache Read (Auto)
$0.10/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
9.1
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
65.9%
Better than 46% of models compared
HLE
Humanity's Last Exam
6.8%
Better than 50% of models compared
IFBench
Instruction-following benchmark
33.1%
Better than 21% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
10.2%
Better than 7% of models compared
AA-LCR
Long context reasoning evaluation
22.7%
Better than 35% of models compared
SciCode
Python programming for scientific computing
30.4%
Better than 45% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
6.1%
AIME 2025
American Invitational Mathematics Examination 2025
66.3%
Better than 61% of models compared
AIME
American Invitational Mathematics Examination
72.7%
Better than 82% of models compared
MMLU-Pro
Professional and academic subject knowledge
77.7%
Better than 58% of models compared
Last updated Jul 15, 2026
Artificial AnalysisBetter than 34% of models compared
LiveCodeBench
Contamination-free coding benchmark
51.5%
Better than 58% of models compared
Math-500
Diverse mathematical problem solving benchmark
97.5%
Better than 89% of models compared
