Compare models
Comparing 2models. Drop the URL into a doc — it's permalinked.
| Field | openai/gpt-4o | anthropic/claude-3-5-sonnet-20241022 |
|---|---|---|
| Provider | openai | anthropic |
| Model ID | gpt-4o | claude-3-5-sonnet-20241022 |
| Context | 128K | 200K |
| Max output | 16K | 8K |
| Input / 1M | $2.50 | $3.00 |
| Output / 1M | $10.00 | $15.00 |
| Cached input / 1M | $1.25 | $0.30 |
| Avg cost / 1M | $6.25 | $9.00 |
| Speed | 110 t/s | 80 t/s |
| Quality index | 71.0 | 70.0 |
| MMLU | 88.7 | 88.7 |
| GPQA | 53.6 | 65.0 |
| HumanEval | 90.2 | 92.0 |
| MATH | 76.6 | 78.3 |
| SWE-bench | — | — |
| Arena Elo | 1338 | — |
| Tools | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Thinking | — | — |
| Streaming | ✓ | ✓ |
| JSON mode | ✓ | — |
| Structured output | ✓ | — |
| Prompt cache | — | ✓ |
Same data, in your terminal: relay models compare 4o anthropic/claude-3-5-sonnet-20241022