Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
claude-3.7-sonnet
anthropic
Context200K tokens
Input Price$3 / 1M tokens
Output Price$15 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $3 / 1M tokens | $2 / 1M tokens |
| Output Price | $15 / 1M tokens | $8 / 1M tokens |
Capabilities | ||
| Context Window | 200K tokens | 1047576 tokens |
| Capabilities | tools | tools |
| Input type | text, image | text, image |
Category Scores | ||
| Overall Average | 57.8 | 52.2 |
| Maths | 56.3 | 34.7 |
| Finance | 53.1 | 39.0 |
| Science | 72.3 | 66.1 |
| Writing | 60.8 | 56.6 |
| Academia | 63.5 | 54.9 |
| Marketing | 62.5 | 59.0 |
| Programming | 35.8 | 32.2 |
| Vision | N/A | 74.8 |
Benchmark Tests | ||
| HLE | 10.3 | 4.6 |
| AIME | 48.7 | 43.7 |
| GPQA | 77.2 | 66.5 |
| MMLU | _ | 90.2 |
| MMMU | _ | 74.8 |
| SciCode | 40.3 | 38.1 |
| MATH-500 | 94.7 | 91.3 |
| MMLU-Pro | 83.7 | 80.6 |
| LiveCodeBench | 47.3 | 45.7 |
| AA Math Index | 56.3 | 34.7 |
| AA Coding Index | 35.8 | 32.2 |
| AAII | 49.9 | 43.4 |
claude-3.7-sonnet Advantages
- • Higher benchmark scores (57.8 vs 52.2)
gpt-4.1 Advantages
- • Lower input token cost ($2 / 1M tokens vs $3 / 1M tokens)
- • Larger context window (1047576 tokens vs 200K tokens)