NVIDIA
NVIDIA's optimized Llama-based model fine-tuned with synthetic data for strong instruction following.
Running this yourself: likely needs a high-memory cloud gpu.
65.5
Quality Score
1205
Arena ELO
70B
Parameters
33K
Context
Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.
This model has normalized benchmark rows, so scores here are directly comparable across benchmark sources.
Sign in to join the discussion
620.0K
Downloads
1.1K
Likes
Oct 2024
Released
These are recent benchmark or leaderboard claims from official provider sources. They are useful for freshness and context, but they are not treated the same as normalized independent benchmark rows.
Llama-3.1-Nemotron-70B-Instruct-HF - Arena-Hard-Auto
Arena-Hard-Auto official Gemini-2.5 judged score 10.3 with CI -0.8/1
View sourceTry NVIDIA NIM APIs
Login Terms of Use Privacy Policy Your Privacy Choices Contact Copyright © 2026 NVIDIA Corporation Models Deploy and scale models on your GPU infrastructure of choice with NVIDIA NIM inference microservices Optimized by NVIDIA Launch from Hugging Face Beta Filters Free Endpoint 42 Partner Endpoint 49 Download Available 113 Use Case Retrieval Augmented Generation 14 Drug Discovery 13 Image-to-Text 11 Code Generation 10 Speech-to-Text 9 Show more Inference Providers Deep Infra
View source1205
ELO Score
1195 - 1215
95% Confidence
+/-10 points
8.5K
Battles
Feb 15, 2026
Last Updated