Qwen 3 Coder 480B

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.

  • Tool Calling
  • Structured Output

Added Mar 17, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.13
Output
$0.50
Compare provider prices

Specifications

Context window
262K
Max output
65.5K
Parameters
480B / 35B
Total / active
Avg output (7d)
581 tokens
Longer than 49% of models

Benchmarks

Sourced from Artificial Analysis.

Intelligence Index

11.9

Better than 47% of models compared

Agentic work

T²-Bench Telecom (legacy)

Legacy fallback · Conversational AI agents in dual-control scenarios

43.6%

Better than 48% of models compared

Document reasoning

AA-LCR v1.1

Long context reasoning with updated grading

45.7%

Better than 41% of models compared

Reasoning

HLE

Humanity's Last Exam

4.5%

Better than 21% of models compared

IFBench

Instruction-following benchmark

40.5%

Better than 39% of models compared

CritPt

Research-level physics reasoning

0.0%

Coding

Terminal-Bench Hard (legacy)

Legacy fallback · Agentic coding and terminal use

18.9%

Better than 59% 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%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

61.8%

Better than 37% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

45.7%

Better than 41% of models compared

Last updated Oct 3, 2026

Artificial Analysis

Providers

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

Loading provider options…