Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
DeepSeek-R1-Distill-Llama-70B
deepinfra
Context131072 tokens
Input Price$0.23 / 1M tokens
Output Price$0.69 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.23 / 1M tokens | $3 / 1M tokens |
| Output Price | $0.69 / 1M tokens | $15 / 1M tokens |
Capabilities | ||
| Context Window | 131072 tokens | 256K tokens |
| Capabilities | tools | |
| Input type | text | text |
Category Scores | ||
| Overall Average | 45.9 | 71.3 |
| Academia | 48.0 | 76.4 |
| Finance | 55.5 | 81.0 |
| Marketing | 22.6 | 51.5 |
| Maths | 80.2 | 96.7 |
| Programming | 28.9 | 63.8 |
| Science | 65.2 | 87.6 |
| Writing | 21.2 | 42.2 |
Benchmark Tests | ||
| AIME | 67.0 | 94.3 |
| AA Coding Index | 28.9 | 63.8 |
| AAII | 30.8 | 65.3 |
| AA Math Index | 80.2 | 96.7 |
| GPQA | 65.2 | 87.6 |
| HLE | 6.1 | 23.9 |
| LiveCodeBench | 26.6 | 81.9 |
| MATH-500 | 93.5 | 99.0 |
| MMLU-Pro | 79.5 | 86.6 |
| SciCode | 31.2 | 45.7 |
DeepSeek-R1-Distill-Llama-70B Advantages
- • Lower input token cost ($0.23 / 1M tokens vs $3 / 1M tokens)
grok-4 Advantages
- • Higher benchmark scores (71.3 vs 45.9)
- • Larger context window (256K tokens vs 131072 tokens)