Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
llama-3.3-70b-instruct
deepinfra
Context131072 tokens
Input Price$0.04 / 1M tokens
Output Price$0.12 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.04 / 1M tokens | $2 / 1M tokens |
| Output Price | $0.12 / 1M tokens | $8 / 1M tokens |
Capabilities | ||
| Context Window | 131072 tokens | 1047576 tokens |
| Capabilities | tools | tools |
| Input type | text | text, image |
Category Scores | ||
| Overall Average | 31.3 | 52.2 |
| Academia | 39.0 | 54.9 |
| Finance | 17.8 | 39.0 |
| Marketing | 41.5 | 59.0 |
| Maths | 7.7 | 34.7 |
| Programming | 19.2 | 32.2 |
| Science | 52.8 | 66.1 |
| Writing | 41.0 | 56.6 |
| Vision | N/A | 74.8 |
Benchmark Tests | ||
| AIME | 30.0 | 43.7 |
| AA Coding Index | 19.2 | 32.2 |
| AAII | 27.9 | 43.4 |
| AA Math Index | 7.7 | 34.7 |
| GPQA | 50.2 | 66.5 |
| HLE | 4.0 | 4.6 |
| HumanEval | 88.4 | _ |
| LiveCodeBench | 28.8 | 45.7 |
| MATH-500 | 77.3 | 91.3 |
| MMLU | 86.0 | 90.2 |
| MMLU-Pro | 70.1 | 80.6 |
| MMMU | _ | 74.8 |
| SciCode | 26.0 | 38.1 |
llama-3.3-70b-instruct Advantages
- • Lower input token cost ($0.04 / 1M tokens vs $2 / 1M tokens)
gpt-4.1 Advantages
- • Higher benchmark scores (52.2 vs 31.3)
- • Larger context window (1047576 tokens vs 131072 tokens)