Skip to content

Qwen3 Coder 30B A3B Instruct

by AlibabaRank #325Score 40.0

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...

Performance Overview

Score
40.0
Rank
#325
24h Change
0
7d Change
0
State
stable
Confidence
high

Signal Scores

SignalNormalizedWeightContributionFreshness
Capabilities
capability
50.030%15.02026-08-08T12:23:37.700Z
Pricing
pricing_tier
99.725%24.92026-08-08T12:23:37.700Z
Context Window
context_window
86.015%12.92026-08-08T12:23:37.700Z
Recency
recency
64.915%9.72026-08-08T12:23:37.700Z
Output Capacity
output_capacity
75.015%11.32026-08-08T12:23:37.700Z

Top Drivers

positive
Pricing
$0.27/M output tokens
$0.27
neutral
Capabilities
Supports tools, JSON mode, streaming
3/7
positive
Context Window
262K token context window
262K
positive
Output Capacity
Up to 33K output tokens per request
33K

Capabilities

CapabilitySupported
VisionNo
ReasoningNo
JSON ModeYes
StreamingYes
Function CallingYes
Web SearchNo

Pricing

Input / 1M tokens
$0.07
Output / 1M tokens
$0.27
Context Window
262K
Max Output
33K

Related Models

Related

Qwen3 Coder 30B A3B Instruct Tracker - Performance History | LM Market Cap