# Llama Nemotron Super 49B v1.5

Llama Nemotron Super 49B v1.5 is an AI model released by NVIDIA on Jul 25 2025. It has 49B parameters, a 128k context window and open weight. Tracked results include 71.97% on GPQA Diamond, 73.58% on LiveCodeBench and 7.64% on Humanity's Last Exam (text only, no tools).

## Facts

| Field | Value |
| --- | --- |
| Model | Llama Nemotron Super 49B v1.5 |
| Developer | NVIDIA |
| Release date | Friday, Jul 25 2025 |
| Licensing | Open Weight |
| Parameters | 49B |
| Context window | 128k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| LiveCodeBench | 73.58% | Lab | Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. |
| Humanity's Last Exam (text only, no tools) | 7.64% | Lab | accuracy on the 2,158 text-only questions without tools |
| MATH-500 | 97.4% | Lab | accuracy on the 500-problem MATH subset |
| AIME 2024 | 87.5% | Lab | single-answer accuracy on the 2024 invitational mathematics exam without tools |
| AIME 2025 | 82.71% | Lab | single-answer accuracy on the 2025 invitational mathematics exam without tools |
| GPQA Diamond | 71.97% | Lab | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |
| MMLU-Pro | 79.53% | Lab | accuracy on the ten-option MMLU-Pro benchmark |

## About Llama Nemotron Super 49B v1.5

NVIDIA released Llama Nemotron Super 49B v1.5 in July 2025 as an update to its 49B Super tier. NVIDIA derived that tier from Meta’s Llama 3.3 70B Instruct through architecture search and distillation. It improved reasoning, coding, instruction following and function calling within the same size tier.

NVIDIA published the weights and the evaluation recipes. With reasoning enabled, the card reported 71.97% on GPQA and 97.4% on MATH-500.

## Questions and answers

### When was Llama Nemotron Super 49B v1.5 released?

Llama Nemotron Super 49B v1.5 was released by NVIDIA on Friday, Jul 25 2025.

### Who made Llama Nemotron Super 49B v1.5?

Llama Nemotron Super 49B v1.5 was built by NVIDIA. The dominant AI chipmaker, publishing the open Nemotron model family. Ships weights, datasets and training recipes to seed demand for its hardware rather than to sell a chatbot.

### What benchmark scores did Llama Nemotron Super 49B v1.5 get?

Llama Nemotron Super 49B v1.5 reports 7 tracked benchmark scores — LiveCodeBench: 73.58%; Humanity's Last Exam (text only, no tools): 7.64%; MATH-500: 97.4%; AIME 2024: 87.5%; AIME 2025: 82.71%; GPQA Diamond: 71.97%; MMLU-Pro: 79.53%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of Llama Nemotron Super 49B v1.5?

Llama Nemotron Super 49B v1.5 has a context window of 128k. Providers may specify separate input and output token limits.

### How many parameters does Llama Nemotron Super 49B v1.5 have?

Llama Nemotron Super 49B v1.5 is reported at 49B parameters.

### Is Llama Nemotron Super 49B v1.5 open source?

Partly. Llama Nemotron Super 49B v1.5 is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after Llama Nemotron Super 49B v1.5?

NVIDIA's previous tracked release was Llama Nemotron Nano 4B v1.1 on May 20 2025, 66 days earlier. It was followed by Nemotron Nano 2 on Aug 18 2025.


---

Canonical page: https://aireleasetracker.com/model/nvidia/llama-nemotron-super-49b-v1.5
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.
