Compare models
Comparing 2models. Drop the URL into a doc — it's permalinked.
| Field | anthropic/claude-sonnet-4-5 | openai/gpt-4o |
|---|---|---|
| Provider | anthropic | openai |
| Model ID | claude-sonnet-4-5 | gpt-4o |
| Context | 200K | 128K |
| Max output | 64K | 16K |
| Input / 1M | $3.00 | $2.50 |
| Output / 1M | $15.00 | $10.00 |
| Cached input / 1M | $0.30 | $1.25 |
| Avg cost / 1M | $9.00 | $6.25 |
| Speed | 95 t/s | 110 t/s |
| Quality index | 73.0 | 71.0 |
| MMLU | 88.7 | 88.7 |
| GPQA | 71.5 | 53.6 |
| HumanEval | 89.1 | 90.2 |
| MATH | 91.8 | 76.6 |
| SWE-bench | 49.0 | — |
| Arena Elo | — | 1338 |
| Tools | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Thinking | ✓ | — |
| Streaming | ✓ | ✓ |
| JSON mode | — | ✓ |
| Structured output | ✓ | ✓ |
| Prompt cache | ✓ | — |
Same data, in your terminal: relay models compare sonnet-4.5 4o