Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
DeepSeek-R1
deepinfra
Context16K tokens
Input Price$0.75 / 1M tokens
Output Price$2.4 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.75 / 1M tokens | $2 / 1M tokens |
| Output Price | $2.4 / 1M tokens | $8 / 1M tokens |
Capabilities | ||
| Context Window | 16K tokens | 1047576 tokens |
| Capabilities | tools | tools |
| Input type | text | text, image |
Category Scores | ||
| Overall Average | 68.7 | 56.8 |
| Academia | 66.7 | 54.9 |
| Finance | 72.9 | 55.5 |
| Marketing | 60.1 | 54.4 |
| Maths | 93.8 | 67.5 |
| Programming | 58.7 | 41.9 |
| Science | 81.3 | 66.5 |
| Writing | 47.5 | 39.2 |
| Vision | N/A | 74.8 |
Benchmark Tests | ||
| AIME | 89.3 | 43.7 |
| AA Coding Index | 58.7 | 41.9 |
| AAII | 52.0 | 43.4 |
| AA Math Index | 93.8 | 67.5 |
| DROP | 92.2 | _ |
| GPQA | 81.3 | 66.5 |
| HLE | 14.9 | 4.6 |
| LiveCodeBench | 77.0 | 45.7 |
| MATH-500 | 98.3 | 91.3 |
| MMLU | 90.8 | 90.2 |
| MMLU-Pro | 84.5 | 80.6 |
| MMMU | _ | 74.8 |
| SciCode | 40.3 | 38.1 |
DeepSeek-R1 Advantages
- • Higher benchmark scores (68.7 vs 56.8)
- • Lower input token cost ($0.75 / 1M tokens vs $2 / 1M tokens)
gpt-4.1 Advantages
- • Larger context window (1047576 tokens vs 16K tokens)