Source: Artificial Analysis / Qwen3 235B A22B 2507 (Reasoning)LMSpeed rank: #72 / 113Updated: Jul 9, 2026Confidence: 4
6869.6 tok/s
6968.0 tok/s
7067.2 tok/s
7166.7 tok/s
72Qwen3 235B A22B Instruct 250766.4 tok/s
73
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 ...
Scores across benchmark categories on a 0-100 scale.
Input and output token limits for this model, plus how it ranks on long-context understanding.
2 metrics
2 metrics
5 metrics
2 metrics
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.Artificial AnalysisStandard benchmark data may include BenchLM and other public sources.