DeepSeek
DeepSeek V3 0324 is a DeepSeek model profile, from a family known for strong reasoning, coding, and cost-conscious API models such as R1 and V-series releases. This page separates the public release context from measured benchmark performance so you can inspect its quality and efficiency directly.
DeepSeek release notesRank #221 across 526
Rank #199 across 436
Rank #219 across 357
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 | 22.3 | #221 |
| Artificial Analysis Coding Index | coding | 22.0 | #199 |
| Artificial Analysis Math Index | math | 41.0 | #157 |
| MMLU-Pro | reasoning | 81.9% | #78 |
| reasoning |
| 65.5% |
| #264 |
| Humanity's Last Exam | reasoning | 5.2% | #292 |
| LiveCodeBench | coding | 40.5% | #178 |
| SciCode | coding, reasoning | 35.8% | #196 |
| MATH-500 | math | 94.2% | #47 |
| AIME | math | 52.0% | #54 |
| Blended Price | cost | $1.21/M | #219 |
| Input Price | cost | $1.20/M | #248 |
| Output Price | cost | $1.25/M | #152 |
| Value Index | cost, overall | 18.4 | #222 |