DeepSeek
DeepSeek R1 0528 (May '25)
DeepSeek-R1 provides customers a state-of-the-art reasoning model, optimized for general reasoning tasks, math, science, and code generation.
DeepSeek release notesModel Snapshot
TypeLanguage
ReleaseJan 20, 2025
Context128,000
Tagsreasoning, tool-use, implicit-caching
Overall
Rank #173 across 526
27.1
Coding
Rank #180 across 436
24.0
Blended Price
Rank #254 across 357
$2.06/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 Output8,192
Streaming speed is not measured for this model yet.
Pricing
Blended$2.06/M
Input$1.35/M
Output$4.20/M
Catalog$1.35/M in / $5.40/M out
Metadata
Providers
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 27.1 | #173 |
| Artificial Analysis Coding Index | coding | 24.0 | #180 |
| Artificial Analysis Math Index | math | 76.0 | #78 |
| MMLU-Pro | reasoning | 84.9% | #35 |