Provider logo

Qwen 3 Coder 480B

qwen/qwen3-coder
Provider logo

Qwen 3 Coder 480B

qwen/qwen3-coder

Qwen 3 Coder 480B, a 480 billion total parameter model with 35B active, and 160 total experts with 8 active. Performs similar to Claude 4 Sonnet in coding benchmarks, but does so at a much lower price.

Added Mar 17, 2026

Model weights

Context Window

262.0K

Max Output

65.5K

Input Price (Auto)

$0.13/1M

Output Price (Auto)

$0.50/1M

Cache Read (Auto)

$0.065/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

18.0

Better than 55% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

61.8%

Better than 43% of models compared

HLE

Humanity's Last Exam

4.4%

Better than 22% of models compared

IFBench

Instruction-following benchmark

40.5%

Better than 40% of models compared

T²-Bench Telecom

Conversational AI agents in dual-control scenarios

43.6%

Better than 49% of models compared

AA-LCR

Long context reasoning evaluation

42.3%

Better than 55% of models compared

CritPt

Research-level physics reasoning

0.0%

Coding

SciCode

Python programming for scientific computing

35.9%

Better than 61% of models compared

Terminal-Bench Hard

Agentic coding and terminal use

18.9%

Better than 60% of models compared

LiveCodeBench

Contamination-free coding benchmark

58.5%

Better than 64% of models compared

Math

AIME 2025

American Invitational Mathematics Examination 2025

39.3%

Better than 41% of models compared

AIME

American Invitational Mathematics Examination

47.7%

Better than 68% of models compared

Math-500

Diverse mathematical problem solving benchmark

94.2%

Better than 76% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

78.8%

Better than 62% of models compared

AA-Omniscience Accuracy

Proportion of correctly answered questions

15.7%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

44.9%

Last updated Jun 28, 2026

Artificial Analysis

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Loading provider options…

Compare Qwen 3 Coder 480B with similar models from the same provider or model family.

Qwen3 Coder Next

qwen/qwen3-coder-next

Qwen3 Coder Next is an open-weight coding model built on Qwen3-Next-80B-A3B-Base (hybrid attention + MoE). It is agentically trained at scale on executable tasks and environment interaction, delivering strong coding and tool-use performance at lower inference cost. Native 256K context.

Qwen3 Coder Flash

qwen/qwen3-coder-flash

A speed‑optimized and budget‑friendly sibling to Coder Plus. Excellent at code generation and agentic workflows (tool use, environment interaction) with solid general‑purpose ability.

Qwen3 Coder Plus

qwen/qwen3-coder-plus

Alibaba’s proprietary upgrade to the open‑weights Qwen3 Coder 480B A35B. A coding‑first agent model with strong tool use and environment control for autonomous programming, while remaining capable at general tasks.

Qwen3.6 35B A3B Thinking

Qwen/Qwen3.6-35B-A3B:thinking

Qwen3.6 35B A3B is a native vision-language MoE model with hybrid attention. Compared to Qwen3.5 35B A3B, Alibaba reports stronger agentic coding, mathematical and code reasoning, and better spatial understanding (including object localization and detection).

Qwen3.6 35B A3B

Qwen/Qwen3.6-35B-A3B

Qwen3.6 35B A3B is a native vision-language MoE model with hybrid attention. Compared to Qwen3.5 35B A3B, Alibaba reports stronger agentic coding, mathematical and code reasoning, and better spatial understanding (including object localization and detection).

Qwen3.5 9B

qwen/qwen3.5-9b

Qwen3.5 9B is a multimodal foundation model from the Qwen 3.5 family, built for efficient reasoning, coding, and visual understanding in a compact 9B architecture.