Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
gemma-3-4b-it
deepinfra
Context131072 tokens
Input Price$0.02 / 1M tokens
Output Price$0.04 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.02 / 1M tokens | $2 / 1M tokens |
| Output Price | $0.04 / 1M tokens | $8 / 1M tokens |
Capabilities | ||
| Context Window | 131072 tokens | 1047576 tokens |
| Capabilities | tools | |
| Input type | text, image | text, image |
Category Scores | ||
| Overall Average | 22.0 | 56.8 |
| Academia | 22.4 | 54.9 |
| Finance | 28.1 | 55.5 |
| Marketing | 11.6 | 54.4 |
| Maths | 41.5 | 67.5 |
| Programming | 9.3 | 41.9 |
| Science | 29.9 | 66.5 |
| Writing | 11.4 | 39.2 |
| Vision | N/A | 74.8 |
Benchmark Tests | ||
| AIME | 6.3 | 43.7 |
| AA Coding Index | 9.3 | 41.9 |
| AAII | 14.8 | 43.4 |
| AA Math Index | 41.5 | 67.5 |
| GPQA | 29.9 | 66.5 |
| HLE | 5.2 | 4.6 |
| HumanEval | 71.3 | _ |
| LiveCodeBench | 11.2 | 45.7 |
| MATH-500 | 76.6 | 91.3 |
| MMLU | _ | 90.2 |
| MMLU-Pro | 42.6 | 80.6 |
| MMMU | _ | 74.8 |
| SciCode | 7.3 | 38.1 |
gemma-3-4b-it Advantages
- • Lower input token cost ($0.02 / 1M tokens vs $2 / 1M tokens)
gpt-4.1 Advantages
- • Higher benchmark scores (56.8 vs 22.0)
- • Larger context window (1047576 tokens vs 131072 tokens)