Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
llama-3.1-70b-instruct
deepinfra
Context131072 tokens
Input Price$0.1 / 1M tokens
Output Price$0.28 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.1 / 1M tokens | $2 / 1M tokens |
| Output Price | $0.28 / 1M tokens | $8 / 1M tokens |
Capabilities | ||
| Context Window | 131072 tokens | 1047576 tokens |
| Capabilities | tools | tools |
| Input type | text | text, image |
Category Scores | ||
| Overall Average | 25.8 | 52.2 |
| Academia | 31.9 | 54.9 |
| Finance | 13.3 | 39.0 |
| Marketing | 33.3 | 59.0 |
| Maths | 4.0 | 34.7 |
| Programming | 17.6 | 32.2 |
| Science | 47.2 | 66.1 |
| Writing | 33.6 | 56.6 |
| Vision | N/A | 74.8 |
Benchmark Tests | ||
| AIME | 17.3 | 43.7 |
| AA Coding Index | 17.6 | 32.2 |
| AAII | 22.6 | 43.4 |
| AA Math Index | 4.0 | 34.7 |
| DROP | 79.6 | _ |
| GPQA | 41.3 | 66.5 |
| HLE | 4.6 | 4.6 |
| HumanEval | 80.5 | _ |
| LiveCodeBench | 23.2 | 45.7 |
| MATH-500 | 64.9 | 91.3 |
| MMLU | 83.6 | 90.2 |
| MMLU-Pro | 67.0 | 80.6 |
| MMMU | _ | 74.8 |
| SciCode | 26.7 | 38.1 |
llama-3.1-70b-instruct Advantages
- • Lower input token cost ($0.1 / 1M tokens vs $2 / 1M tokens)
gpt-4.1 Advantages
- • Higher benchmark scores (52.2 vs 25.8)
- • Larger context window (1047576 tokens vs 131072 tokens)