Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
gemini-2.5-flash-lite
openrouter
Context1048576 tokens
Input Price$0.1 / 1M tokens
Output Price$0.4 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.1 / 1M tokens | $2 / 1M tokens |
| Output Price | $0.4 / 1M tokens | $8 / 1M tokens |
Capabilities | ||
| Context Window | 1048576 tokens | 1047576 tokens |
| Capabilities | tools | tools |
| Input type | text, image | text, image |
Category Scores | ||
| Overall Average | 44.7 | 52.2 |
| Academia | 47.4 | 54.9 |
| Finance | 32.7 | 39.0 |
| Marketing | 43.2 | 59.0 |
| Maths | 35.3 | 34.7 |
| Programming | 19.9 | 32.2 |
| Science | 62.1 | 66.1 |
| Vision | 72.9 | 74.8 |
| Writing | 43.9 | 56.6 |
Benchmark Tests | ||
| AIME | 50.0 | 43.7 |
| AA Coding Index | 19.9 | 32.2 |
| AAII | 30.1 | 43.4 |
| AA Math Index | 35.3 | 34.7 |
| GPQA | 64.6 | 66.5 |
| HLE | 3.7 | 4.6 |
| LiveCodeBench | 40.0 | 45.7 |
| MATH-500 | 92.6 | 91.3 |
| MMLU | _ | 90.2 |
| MMLU-Pro | 72.4 | 80.6 |
| MMMU | 72.9 | 74.8 |
| SciCode | 17.7 | 38.1 |
gemini-2.5-flash-lite Advantages
- • Lower input token cost ($0.1 / 1M tokens vs $2 / 1M tokens)
- • Larger context window (1048576 tokens vs 1047576 tokens)
gpt-4.1 Advantages
- • Higher benchmark scores (52.2 vs 44.7)