DeepSeek
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
DeepSeek release notesRank #172 across 566
Rank #101 across 222
Rank #88 across 371
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
Streaming speed is not measured for this model yet.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 25.4 | #172 |
| Artificial Analysis Coding Index | coding | 44.2 | #101 |
| Artificial Analysis Math Index | math | 87.7 | #41 |
| MMLU-Pro | reasoning | 85.0% | #36 |
| reasoning |
| 79.7% |
| #146 |
| Humanity's Last Exam | reasoning | 13.8% | #148 |
| LiveCodeBench | coding | 78.9% | #32 |
| SciCode | coding, reasoning | 37.7% | #187 |
| Blended Price | cost | $0.315/M | #88 |
| Input Price | cost | $0.280/M | #119 |
| Output Price | cost | $0.420/M | #70 |
| Value Index | cost, overall | 80.6 | #42 |