Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
claude-sonnet-4.5
anthropic
Context200K tokens
Input Price$3 / 1M tokens
Output Price$15 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $1 / 1M tokens | $3 / 1M tokens |
| Output Price | $3 / 1M tokens | $15 / 1M tokens |
Capabilities | ||
| Context Window | 131072 tokens | 200K tokens |
| Capabilities | tools | tools, reasoning |
| Input type | text | text, image |
Category Scores | ||
| Overall Average | 56.7 | 71.4 |
| Academia | 63.3 | 73.0 |
| Finance | 53.8 | 75.3 |
| Marketing | 57.6 | 69.2 |
| Maths | 57.3 | 88.0 |
| Programming | 38.1 | 49.8 |
| Science | 70.8 | 77.7 |
| Writing | 56.1 | 66.9 |
Benchmark Tests | ||
| AA Coding Index | 38.1 | 49.8 |
| AAII | 50.4 | 62.7 |
| AA Math Index | 57.3 | 88.0 |
| GPQA | 76.3 | 83.4 |
| HLE | 6.3 | 17.3 |
| HumanEval | 94.5 | _ |
| LiveCodeBench | 61.0 | 71.4 |
| MMLU | 90.2 | _ |
| MMLU-Pro | 82.2 | 87.5 |
| SciCode | 30.7 | 44.7 |
kimi-k2 Advantages
- • Lower input token cost ($1 / 1M tokens vs $3 / 1M tokens)
claude-sonnet-4.5 Advantages
- • Higher benchmark scores (71.4 vs 56.7)
- • Larger context window (200K tokens vs 131072 tokens)