Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
claude-sonnet-4
anthropic
Context200K tokens
Input Price$3 / 1M tokens
Output Price$15 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $2.5 / 1M tokens | $3 / 1M tokens |
| Output Price | $10 / 1M tokens | $15 / 1M tokens |
Capabilities | ||
| Context Window | 128K tokens | 200K tokens |
| Capabilities | tools | tools |
| Input type | text, image | text, image |
Category Scores | ||
| Overall Average | 31.7 | 54.6 |
| Academia | 40.7 | 59.9 |
| Finance | 16.5 | 41.2 |
| Marketing | 34.4 | 56.0 |
| Maths | 6.0 | 38.0 |
| Programming | 32.1 | 41.1 |
| Science | 56.6 | 71.1 |
| Writing | 35.8 | 55.1 |
| Vision | N/A | 74.4 |
Benchmark Tests | ||
| AIME | 15.0 | 40.7 |
| AA Coding Index | 32.1 | 41.1 |
| AAII | 27.0 | 44.4 |
| AA Math Index | 6.0 | 38.0 |
| GPQA | 54.3 | 75.4 |
| HLE | 3.3 | 4.0 |
| LiveCodeBench | 30.9 | 44.9 |
| MATH-500 | 75.9 | 93.4 |
| MMLU-Pro | 74.8 | 83.7 |
| MMMU | _ | 74.4 |
| SciCode | 33.3 | 37.3 |
gpt-4o Advantages
- • Lower input token cost ($2.5 / 1M tokens vs $3 / 1M tokens)
claude-sonnet-4 Advantages
- • Higher benchmark scores (54.6 vs 31.7)
- • Larger context window (200K tokens vs 128K tokens)