Llama 3.3 Nemotron Super 49B V1.5
NVIDIA's Llama 3.3 Nemotron Super 49B V1.5: an instruction-tuned language model optimized for agentic RAG, tool calling, and complex reasoning tasks.
Model Overview
Capabilities, design details, and architectural traits
Llama 3.3 Nemotron Super 49B V1.5 - instruction-tuned reasoning
Llama 3.3 Nemotron Super 49B V1.5 is NVIDIA's instruction-tuned model for advanced dialogue and reasoning tasks. It is also presented as a reasoning and chat model with agentic workflow support.
| Distinctive trait | What is documented |
|---|---|
| Advanced dialogue and reasoning | Described as a large, instruction-tuned model for advanced dialogue and reasoning tasks. |
| Agentic workflow focus | Documented for RAG and tool calling use cases. |
| Reasoning/chat positioning | Presented as a reasoning and chat model rather than a general chat-only model. |
Documented workflow
The model is described as post-trained for reasoning, human chat preferences, and agentic tasks such as RAG and tool calling. The official docs also place it in NVIDIA's Nemotron family of instruction-tuned models.
Benchmark Performance
Independent evaluations · Artificial Analysis
Accuracy & Capability Details
Compare Models Side-by-Side
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | NVIDIA | Anthropic | Anthropic |
| Release Date | July 25, 2025 | September 22, 2026 | September 28, 2026 |
| Knowledge Cutoff | Mar 2024 | - | Jun 2026 |
| Context & Limits | |||
| Context Window | 131K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | $0.40 Best Input Pricing | $4 | $2 |
| Output Pricing | $0.40 Best Output Pricing | $20 | $10 |
| Modalities | |||
| Inputs | text | textimagefile | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 7.4 | 57.6 Best Intelligence Index | 56.0 |
| Coding Index | - | - | - |
| Agentic Index | - | - | - |
Humanity's Last Exam
Extremely difficult logical reasoning and knowledge.
Long Context Reasoning
Logical reasoning over long context windows.
SciCode Benchmark
Scientific coding and mathematical modeling.
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
Explore more from NVIDIA
Other models by NVIDIA
Top AI Models
Leading alternatives by intelligence score
