Private AI
Qwen3-30B-A3B-Instruct-2507 is a MoE causal language model featuring 30.5B total parameters and 3.3B active parameters. Running inside a TEE (Trusted Execution Environment), with provider attestation support.
Context Window
262.0K
Max Output
32.8K
Input Price (Auto)
$0.15/1M
Output Price (Auto)
$0.45/1M
Cache Read (Auto)
$0.075/1M
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
