01Overview02Models03Rankings04Compare05Quiz06Guide

Model

Qwen3-Coder-480B-A35B NO.35

Best open-weights Qwen for agentic coding — great value.

CompareBack to the index

Alibaba Qwen · Qwen · Open · Open weights

Specification

Fig.01 — Qwen — Alibaba Qwen

CHINA

Context window
1.0Mtokens
Max output
66Ktokens
Input price
$0.22/ 1M
Output price
$1.80/ 1M
Cached input
$0.15/ 1M
Throughput
—
Class
Open
Modalities
Text
Weights
Open
Parameters
480B
License
Apache-2.0
Knowledge cutoff
Apr 2025
Released
Jul 2025

Overview

Qwen3-Coder-480B-A35B-Instruct is Alibaba's flagship open-weights coding model, a 480B-parameter MoE with 35B active params and native long context (extendable toward 1M). It is the strongest Qwen for coding and agentic tool use, roughly comparable to Claude Sonnet 4 among open models, and ships under Apache-2.0. Long multi-file agent runs still need more supervision and can drift compared with the Claude/GPT frontier.

Strengths

  • Top-tier open-weights coding ability
  • Apache-2.0 license, self-hostable
  • Strong agentic tool-use for an open model
  • Native long context for whole-repo work

Trade-offs

  • Drifts on long multi-file agent sessions
  • Below frontier reliability without supervision
  • Text-only, no vision
  • Heavy to self-host (480B MoE)

Fit

Best for

  • Self-hosted coding assistants
  • Agentic code generation on a budget
  • Repo-scale code understanding and refactoring
  • Tool-use and browser automation

Not ideal for

  • Unsupervised long-horizon refactors
  • Vision or multimodal tasks

Capabilities

Ten axes, normalized 0–100 and scored the same way across the whole catalog — so a 78 here means what a 78 means anywhere else on the bench.

Fig.02 — Capability radar

0 — 100

Reasoning
72
Coding
78
Math
74
Writing
70
Knowledge
76
Speed
62
Agentic
72
Vision
5
Multilingual
80
Long Context
82

Benchmarks

Public results, with independent third-party runs marked. Bars normalize percentages against 100 and Elo ratings against a 1500 ceiling.

BenchmarkResult
SWE-bench VerifiedIndependentCoding · SWE-bench
67%
SWE-bench ProIndependentCoding · SWE-bench Pro
38.7%
Aider PolyglotIndependentCoding · Aider
61.8%

Alternatives

Models in roughly the same class — the ones worth weighing against this record.

Compare side by side
01GLM-4.7Zhipu AIEfficient open coding workhorse for everyday dev tasks.02Kimi K2.6Moonshot AIOpen-weight agentic powerhouse with long context and video input.03DeepSeek-V3.2DeepSeekUltra-cheap open MoE with standout math and efficiency.

Index

PreviousQwen3-30B-A3B-Instruct-2507NextGLM-5.2
All models/EDUCATION