Compare models
Comparing 2models. Drop the URL into a doc — it's permalinked.
| Field | anthropic/claude-haiku-4-5 | openai/gpt-4o-mini |
|---|---|---|
| Provider | anthropic | openai |
| Model ID | claude-haiku-4-5 | gpt-4o-mini |
| Context | 200K | 128K |
| Max output | 8K | 16K |
| Input / 1M | $1.00 | $0.15 |
| Output / 1M | $5.00 | $0.60 |
| Cached input / 1M | $0.10 | $0.07 |
| Avg cost / 1M | $3.00 | $0.38 |
| Speed | 165 t/s | 145 t/s |
| Quality index | 60.0 | 60.0 |
| MMLU | 81.2 | 82.0 |
| GPQA | 50.1 | 40.2 |
| HumanEval | 78.3 | 87.2 |
| MATH | 76.5 | 70.2 |
| SWE-bench | — | — |
| Arena Elo | — | — |
| Tools | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Thinking | — | — |
| Streaming | ✓ | ✓ |
| JSON mode | — | ✓ |
| Structured output | ✓ | ✓ |
| Prompt cache | ✓ | — |
Same data, in your terminal: relay models compare haiku-4.5 4o-mini