DeepSeek
DeepSeek R1 (Jan '25)
DeepSeek R1 (Jan '25) 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 notesOperational Metrics
Output Speedn/a
First Tokenn/a
Blended Price$2.36/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseJan 20, 2025
Context Windown/a
Modalitiesn/a
Strength: MMLU-Pro
Rank #37 across 345 models.
84.4%
Strength: MATH-500
Rank #31 across 201 models.
96.6%
Strength: AIME
Rank #44 across 194 models.
68.3%
Watch Area: Value
Rank #261 across 323 models.
8.0
Watch Area: Input $
Rank #253 across 325 models.
$1.68/M
Watch Area: Blended $
Rank #228 across 325 models.
$2.36/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.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 18.8 | #248 |
| Artificial Analysis Coding Index | coding | 15.9 | #232 |
| Artificial Analysis Math Index | math | 68.0 | #101 |
| MMLU-Pro | reasoning | 84.4% | #37 |