Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
gemini-3-flash-preview
gemini
Context1M tokens
Input Price$0.5 / 1M tokens
Output Price$3 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.5 / 1M tokens | $2 / 1M tokens |
| Output Price | $3 / 1M tokens | $8 / 1M tokens |
Capabilities | ||
| Context Window | 1M tokens | 1047576 tokens |
| Capabilities | tools, reasoning | tools |
| Input type | text, image, audio, video | text, image |
Category Scores | ||
| Overall Average | 63.3 | 52.2 |
| Maths | 55.7 | 34.7 |
| Finance | 55.1 | 39.0 |
| Science | 81.1 | 66.1 |
| Writing | 62.8 | 56.6 |
| Academia | 72.5 | 54.9 |
| Marketing | 63.0 | 59.0 |
| Programming | 53.1 | 32.2 |
| Vision | N/A | 74.8 |
Benchmark Tests | ||
| HLE | 14.1 | 4.6 |
| AIME | _ | 43.7 |
| GPQA | 90.4 | 66.5 |
| MMLU | _ | 90.2 |
| MMMU | _ | 74.8 |
| SciCode | 49.9 | 38.1 |
| MATH-500 | _ | 91.3 |
| MMLU-Pro | 88.2 | 80.6 |
| LiveCodeBench | 79.7 | 45.7 |
| AA Math Index | 55.7 | 34.7 |
| AA Coding Index | 53.1 | 32.2 |
| AAII | 54.5 | 43.4 |
gemini-3-flash-preview Advantages
- • Higher benchmark scores (63.3 vs 52.2)
- • Lower input token cost ($0.5 / 1M tokens vs $2 / 1M tokens)
gpt-4.1 Advantages
- • Larger context window (1047576 tokens vs 1M tokens)