Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
llama-4-maverick
deepinfra
Context1048576 tokens
Input Price$0.15 / 1M tokens
Output Price$0.6 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.15 / 1M tokens | $2 / 1M tokens |
| Output Price | $0.6 / 1M tokens | $8 / 1M tokens |
Capabilities | ||
| Context Window | 1048576 tokens | 1047576 tokens |
| Capabilities | tools | |
| Input type | text, image | text, image |
Category Scores | ||
| Overall Average | 53.9 | 56.8 |
| Academia | 52.1 | 54.9 |
| Finance | 49.8 | 55.5 |
| Marketing | 49.5 | 54.4 |
| Maths | 63.9 | 67.5 |
| Programming | 36.4 | 41.9 |
| Science | 68.5 | 66.5 |
| Vision | 73.4 | 74.8 |
| Writing | 37.6 | 39.2 |
Benchmark Tests | ||
| AIME | 39.0 | 43.7 |
| AA Coding Index | 36.4 | 41.9 |
| AAII | 35.8 | 43.4 |
| AA Math Index | 63.9 | 67.5 |
| GPQA | 68.5 | 66.5 |
| HLE | 4.8 | 4.6 |
| LiveCodeBench | 39.7 | 45.7 |
| MATH-500 | 88.9 | 91.3 |
| MMLU | 85.5 | 90.2 |
| MMLU-Pro | 80.7 | 80.6 |
| MMMU | 73.4 | 74.8 |
| SciCode | 33.1 | 38.1 |
llama-4-maverick Advantages
- • Lower input token cost ($0.15 / 1M tokens vs $2 / 1M tokens)
- • Larger context window (1048576 tokens vs 1047576 tokens)
gpt-4.1 Advantages
- • Higher benchmark scores (56.8 vs 53.9)