Compare the top 5 language models by average benchmark performance
Note: This comparison shows the top 5 models ranked by average benchmark score. You can select specific models to compare in a future update.
| Feature | Llama-3.3 Nemotron Super 49B | Qwen2.5-Coder 32B Instruct | Qwen2.5 72B Instruct | Llama 3.1 Nemotron Nano 8B | Qwen2.5 32B Instruct |
|---|---|---|---|---|---|
Organization | NVIDIA | Alibaba / Qwen | Alibaba / Qwen | NVIDIA | Alibaba / Qwen |
Release Date | 2025-03-01 | 2024-11-12 | 2024-09-19 | 2025-01-06 | 2024-09-19 |
License | Apache 2.0 | Apache 2.0 | Apache 2.0 | Apache 2.0 | Apache 2.0 |
Multimodal | |||||
Average Score | 91.3% | 90.2% | 88.2% | 84.6% | 84.0% |
| MBPP | 91.3% | 90.2% | 88.2% | 84.6% | 84.0% |
| Min Input Price(cents per 1M tokens) | - | - | - | - | - |
| Min Output Price(cents per 1M tokens) | - | - | - | - | - |