BenchmarksToday
Qwen3-Coder-480B-A35B-Instruct - SWE-Bench Verified
SWE-Bench Verified resolved rate 55.4
View sourceQwen
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
Running this yourself: likely needs a high-memory cloud gpu.
20.1
Quality Score
---
Arena ELO
480B
Parameters
1M
Context
Sign in to join the discussion
0
Downloads
0
Likes
Jul 2025
Released
Benchmarks
5
Open Source
1
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
SWE-Bench Verified resolved rate 55.4
View sourceSWE-Bench Verified resolved rate 69.6
View sourceSWE-Bench Verified resolved rate 69.6
SWE-Bench Verified resolved rate 55.4
View sourceGAIA score 44.2 from WA0824
View sourceQwen3 Coder 480B A35B is now available through local Ollama runtime and Ollama Cloud. 256K context window listed. Alibaba's performant long context models for agentic and coding tasks.
SWE-Bench Verified resolved rate 55.4
SWE-Bench Verified resolved rate 69.6
SWE-Bench Verified resolved rate 69.6
SWE-Bench Verified resolved rate 55.4