Source: Artificial Analysis / Qwen3 235B A22B (Reasoning)LMSpeed rank: #74 / 113Updated: Jul 9, 2026Confidence: 4
7067.2 tok/s
7166.7 tok/s
7266.4 tok/s
7365.4 tok/s
74Qwen3 235B A22B64.7 tok/s
75
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex r...
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.