Compare models
Comparing 2models. Drop the URL into a doc — it's permalinked.
| Field | groq/llama-3.3-70b-versatile | openai/gpt-4o-mini |
|---|---|---|
| Provider | groq | openai |
| Model ID | llama-3.3-70b-versatile | gpt-4o-mini |
| Context | 131K | 128K |
| Max output | 33K | 16K |
| Input / 1M | $0.59 | $0.15 |
| Output / 1M | $0.79 | $0.60 |
| Cached input / 1M | — | $0.07 |
| Avg cost / 1M | $0.69 | $0.38 |
| Speed | 280 t/s | 145 t/s |
| Quality index | 56.0 | 60.0 |
| MMLU | 86.0 | 82.0 |
| GPQA | 50.5 | 40.2 |
| HumanEval | 88.4 | 87.2 |
| MATH | 77.0 | 70.2 |
| SWE-bench | — | — |
| Arena Elo | — | — |
| Tools | ✓ | ✓ |
| Vision | — | ✓ |
| Thinking | — | — |
| Streaming | ✓ | ✓ |
| JSON mode | ✓ | ✓ |
| Structured output | — | ✓ |
| Prompt cache | — | — |
Same data, in your terminal: relay models compare llama-3.3-70b 4o-mini