Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
claude-opus-4
anthropic
Context200K tokens
Input Price$15 / 1M tokens
Output Price$75 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $15 / 1M tokens | $2.5 / 1M tokens |
| Output Price | $75 / 1M tokens | $10 / 1M tokens |
Capabilities | ||
| Context Window | 200K tokens | 128K tokens |
| Capabilities | tools | tools |
| Input type | text, image | text, image |
Category Scores | ||
| Overall Average | 62.5 | 30.6 |
| Maths | 73.3 | 6.0 |
| Finance | 63.8 | 16.5 |
| Science | 75.0 | 56.6 |
| Writing | 56.8 | 35.8 |
| Academia | 66.9 | 40.7 |
| Marketing | 57.4 | 34.4 |
| Programming | 44.2 | 24.0 |
Benchmark Tests | ||
| HLE | 11.7 | 3.3 |
| AIME | 75.7 | 15.0 |
| GPQA | 79.6 | 54.3 |
| SciCode | 39.8 | 33.3 |
| MATH-500 | 98.2 | 75.9 |
| MMLU-Pro | 87.3 | 74.8 |
| LiveCodeBench | 63.6 | 30.9 |
| AA Math Index | 73.3 | 6.0 |
| AA Coding Index | 44.2 | 24.0 |
| AAII | 54.2 | 27.0 |
claude-opus-4 Advantages
- • Higher benchmark scores (62.5 vs 30.6)
- • Larger context window (200K tokens vs 128K tokens)
gpt-4o Advantages
- • Lower input token cost ($2.5 / 1M tokens vs $15 / 1M tokens)