Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
deepseek-chat-v3.1
deepinfra
Context163840 tokens
Input Price$0.3 / 1M tokens
Output Price$1 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.3 / 1M tokens | $2 / 1M tokens |
| Output Price | $1 / 1M tokens | $8 / 1M tokens |
Capabilities | ||
| Context Window | 163840 tokens | 1047576 tokens |
| Capabilities | tools | tools |
| Input type | text | text, image |
Category Scores | ||
| Overall Average | 53.1 | 52.2 |
| Academia | 59.1 | 54.9 |
| Finance | 47.3 | 39.0 |
| Marketing | 53.8 | 59.0 |
| Maths | 49.7 | 34.7 |
| Programming | 39.0 | 32.2 |
| Science | 69.8 | 66.1 |
| Writing | 53.2 | 56.6 |
| Vision | N/A | 74.8 |
Benchmark Tests | ||
| AIME | _ | 43.7 |
| AA Coding Index | 39.0 | 32.2 |
| AAII | 44.8 | 43.4 |
| AA Math Index | 49.7 | 34.7 |
| GPQA | 73.5 | 66.5 |
| HLE | 6.3 | 4.6 |
| LiveCodeBench | 57.7 | 45.7 |
| MATH-500 | _ | 91.3 |
| MMLU | _ | 90.2 |
| MMLU-Pro | 83.3 | 80.6 |
| MMMU | _ | 74.8 |
| SciCode | 36.7 | 38.1 |
deepseek-chat-v3.1 Advantages
- • Higher benchmark scores (53.1 vs 52.2)
- • Lower input token cost ($0.3 / 1M tokens vs $2 / 1M tokens)
gpt-4.1 Advantages
- • Larger context window (1047576 tokens vs 163840 tokens)