DeepSeek
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.
DeepSeek release notesRank #294 across 526
Rank #248 across 436
Rank #138 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 | 16.5 | #294 |
| Artificial Analysis Coding Index | coding | 16.4 | #248 |
| Artificial Analysis Math Index | math | 26.0 | #195 |
| MMLU-Pro | reasoning | 75.2% | #173 |
| reasoning |
| 55.7% |
| #327 |
| Humanity's Last Exam | reasoning | 3.6% | #470 |
| LiveCodeBench | coding | 35.9% | #194 |
| SciCode | coding, reasoning | 35.4% | #203 |
| MATH-500 | math | 88.7% | #80 |
| AIME | math | 25.3% | #92 |
| Blended Price | cost | $0.523/M | #138 |
| Input Price | cost | $0.400/M | #172 |
| Output Price | cost | $0.890/M | #128 |
| Value Index | cost, overall | 31.5 | #174 |