Qwen: Qwen3 Coder 30B A3B Instruct
Qwen3 Coder 30B A3B is a compact, coding-focused model with decent livecodebench performance and very competitive pricing, though its overall intelligence and reasoning scores are limited — best suited to lightweight coding assistance and cost-sensitive deployments.
Assessment date: March 12, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion. This model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats.
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Qwen3 |
| Parameters | 30B |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.07 | $0.000070 |
| Output | $0.27 | $0.000270 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
