by NVIDIARank #141Score 60.1
Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and...
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 66.7 | 20% | 13.3 | 2026-06-24T09:59:39.283Z |
Benchmarks benchmark | 59.1 | 30% | 17.7 | 2026-06-24T09:59:39.283Z |
Pricing pricing_tier | 99.6 | 15% | 14.9 | 2026-06-24T09:59:39.283Z |
Context Window context_window | 73.1 | 10% | 7.3 | 2026-06-24T09:59:39.283Z |
Recency recency | 86.0 | 15% | 12.9 | 2026-06-24T09:59:39.283Z |
Output Capacity output_capacity | 70.2 | 10% | 7.0 | 2026-06-24T09:59:39.283Z |
| Capability | Supported |
|---|---|
| Vision | No |
| Reasoning | Yes |
| JSON Mode | Yes |
| Streaming | Yes |
| Function Calling | Yes |
| Web Search | No |