Compare models
Comparing 2models. Drop the URL into a doc — it's permalinked.
| Field | nvidia/nemotron-nano-12b-v2-vl | groq/llama-3.3-70b-versatile |
|---|---|---|
| Provider | nvidia | groq |
| Model ID | nemotron-nano-12b-v2-vl | llama-3.3-70b-versatile |
| Context | 131K | 131K |
| Max output | — | 33K |
| Input / 1M | $0.20 | $0.59 |
| Output / 1M | $0.60 | $0.79 |
| Cached input / 1M | — | — |
| Avg cost / 1M | $0.40 | $0.69 |
| Speed | — | 280 t/s |
| Quality index | — | 56.0 |
| MMLU | — | 86.0 |
| GPQA | — | 50.5 |
| HumanEval | — | 88.4 |
| MATH | — | 77.0 |
| SWE-bench | — | — |
| Arena Elo | — | — |
| Tools | — | ✓ |
| Vision | ✓ | — |
| Thinking | — | — |
| Streaming | — | ✓ |
| JSON mode | ✓ | ✓ |
| Structured output | — | — |
| Prompt cache | — | — |
Same data, in your terminal: relay models compare nvidia/nemotron-nano-12b-v2-vl llama-3.3-70b