Benchmarks3mo ago
Qwen3-235B-A22B - Arena-Hard-Auto
Arena-Hard-Auto official Gemini-2.5 judged score 58.4 with CI -1.9/2.1
View sourceQwen
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...
Running this yourself: likely needs a high-memory cloud gpu.
49.4
Quality Score
1367
Arena ELO
235B
Parameters
262K
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.
Arena-Hard-Auto official Gemini-2.5 judged score 58.4 with CI -1.9/2.1
View sourceLiveCodeBench pass@1 80.4 across 1055 tasks
View sourceSWE-Bench Verified resolved rate 69.6
SWE-Bench Verified resolved rate 69.6
View sourceGAIA score 44.2 from WA0824
View sourceQwen3 235B A22B Instruct 2507 is now available through local Ollama runtime. 40K context window listed. Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
Arena-Hard-Auto official Gemini-2.5 judged score 58.4 with CI -1.9/2.1
LiveCodeBench pass@1 80.4 across 1055 tasks
SWE-Bench Verified resolved rate 69.6
SWE-Bench Verified resolved rate 69.6