Source: Artificial Analysis / DeepSeek V3.2 Exp (Non-reasoning)LMSpeed rank: #39 / 138Updated: Jul 9, 2026Confidence: 4
33$0.250/M
33$0.250/M
38$0.270/M
39$0.280/M
39DeepSeek V3.2 Exp$0.280/M
41
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grai...
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
3 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.