Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
gemini-2.5-pro
gemini
Context1M tokens
Input Price$1.25 / 1M tokens
Output Price$10 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $2 / 1M tokens | $1.25 / 1M tokens |
| Output Price | $8 / 1M tokens | $10 / 1M tokens |
Capabilities | ||
| Context Window | 1047576 tokens | 1M tokens |
| Capabilities | tools | tools |
| Input type | text, image | text, image, audio, video |
Category Scores | ||
| Overall Average | 57.5 | 70.0 |
| Academia | 56.6 | 74.2 |
| Finance | 57.1 | 78.7 |
| Marketing | 55.7 | 50.1 |
| Maths | 67.5 | 92.7 |
| Programming | 41.9 | 61.5 |
| Science | 66.5 | 83.7 |
| Vision | 74.8 | 79.6 |
| Writing | 39.5 | 39.4 |
Benchmark Tests | ||
| AIME | 43.7 | 88.7 |
| AA Coding Index | 41.9 | 61.5 |
| AAII | 46.8 | 64.6 |
| AA Math Index | 67.5 | 92.7 |
| GPQA | 66.5 | 83.7 |
| HLE | 4.6 | 21.1 |
| LiveCodeBench | 45.7 | 80.1 |
| MATH-500 | 91.3 | 96.7 |
| MMLU | 90.2 | _ |
| MMLU-Pro | 80.6 | 86.2 |
| MMMU | 74.8 | 79.6 |
| SciCode | 38.1 | 42.8 |
gpt-4.1 Advantages
- • Larger context window (1047576 tokens vs 1M tokens)
gemini-2.5-pro Advantages
- • Higher benchmark scores (70.0 vs 57.5)
- • Lower input token cost ($1.25 / 1M tokens vs $2 / 1M tokens)