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 | $1.25 / 1M tokens | $2 / 1M tokens |
| Output Price | $10 / 1M tokens | $8 / 1M tokens |
Capabilities | ||
| Context Window | 1M tokens | 1047576 tokens |
| Capabilities | tools | tools |
| Input type | text, image, audio, video | text, image |
Category Scores | ||
| Overall Average | 71.4 | 52.2 |
| Academia | 71.7 | 54.9 |
| Finance | 73.7 | 39.0 |
| Marketing | 66.1 | 59.0 |
| Maths | 87.7 | 34.7 |
| Programming | 49.3 | 32.2 |
| Science | 77.9 | 66.1 |
| Vision | 79.6 | 74.8 |
| Writing | 64.9 | 56.6 |
Benchmark Tests | ||
| AIME | 88.7 | 43.7 |
| AA Coding Index | 49.3 | 32.2 |
| AAII | 59.6 | 43.4 |
| AA Math Index | 87.7 | 34.7 |
| GPQA | 83.7 | 66.5 |
| HLE | 21.1 | 4.6 |
| LiveCodeBench | 80.1 | 45.7 |
| MATH-500 | 96.7 | 91.3 |
| MMLU | _ | 90.2 |
| MMLU-Pro | 86.2 | 80.6 |
| MMMU | 79.6 | 74.8 |
| SciCode | 42.8 | 38.1 |
gemini-2.5-pro Advantages
- • Higher benchmark scores (71.4 vs 52.2)
- • Lower input token cost ($1.25 / 1M tokens vs $2 / 1M tokens)
gpt-4.1 Advantages
- • Larger context window (1047576 tokens vs 1M tokens)