Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
llama-4-scout
deepinfra
Context327680 tokens
Input Price$0.08 / 1M tokens
Output Price$0.3 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.08 / 1M tokens | $2 / 1M tokens |
| Output Price | $0.3 / 1M tokens | $8 / 1M tokens |
Capabilities | ||
| Context Window | 327680 tokens | 1047576 tokens |
| Capabilities | tools | |
| Input type | text, image | text, image |
Category Scores | ||
| Overall Average | 46.3 | 56.8 |
| Academia | 43.0 | 54.9 |
| Finance | 42.3 | 55.5 |
| Marketing | 43.9 | 54.4 |
| Maths | 56.4 | 67.5 |
| Programming | 23.5 | 41.9 |
| Science | 57.9 | 66.5 |
| Vision | 69.4 | 74.8 |
| Writing | 33.6 | 39.2 |
Benchmark Tests | ||
| AIME | 28.3 | 43.7 |
| AA Coding Index | 23.5 | 41.9 |
| AAII | 28.1 | 43.4 |
| AA Math Index | 56.4 | 67.5 |
| GPQA | 57.9 | 66.5 |
| HLE | 4.3 | 4.6 |
| LiveCodeBench | 29.9 | 45.7 |
| MATH-500 | 84.4 | 91.3 |
| MMLU | 79.6 | 90.2 |
| MMLU-Pro | 74.8 | 80.6 |
| MMMU | 69.4 | 74.8 |
| SciCode | 17.0 | 38.1 |
llama-4-scout Advantages
- • Lower input token cost ($0.08 / 1M tokens vs $2 / 1M tokens)
gpt-4.1 Advantages
- • Higher benchmark scores (56.8 vs 46.3)
- • Larger context window (1047576 tokens vs 327680 tokens)