Compare models

1 model side by side

Add a second model above to see them side by side.
qwen/qwen3-30b-a3b
Details
Overview
DescriptionAlibaba's efficient Mixture-of-Experts model with 30B total parameters and only 3B activated per token, optimized for fast inference.
AuthorQwen
CategoryText Generation
Context length131K
Providers3
Pricing (per 1M tokens)
Input$0
Output$0
Capabilities
Reasoning
Tool calling
Vision
Streaming
Token activity (30 days)
Usage
Artificial Analysis
Intelligence12.5
Coding13.3
Benchmarks
GPQA Diamond0.5
HLE0.0
MMLU-Pro0.7
IFEval0.3
LiveCodeBench0.3
AIME0.3
MATH-5000.9