DeepSeek
DeepSeek V3.2 Exp (Non-reasoning)
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-grained sparse attention mechanism...
DeepSeek release notesModel Snapshot
ReleaseSep 29, 2025
Context163,840
Overall
Rank #233 across 600
21.3
Coding
No rank
n/a
Blended Price
Rank #89 across 379
$0.315/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Max Output65,536
Streaming speed is not measured for this model yet.
Pricing
Blended$0.315/M
Input$0.280/M
Output$0.420/M
Metadata
Modalities
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 21.3 | #233 |
| Artificial Analysis Math Index | math | 57.7 | #122 |
| MMLU-Pro | reasoning | 83.6% | #49 |
| GPQA | reasoning | 73.8% | #229 |
| Humanity's Last Exam |