Llama 3.1 Nemotron Ultra 253B v1 — benchmark results
NVIDIA Llama 3.1 Nemotron Ultra 253B v1 model row. Provider: NVIDIA. Released 2025-04-07. Access: Open.
Unified ELO 1510 ± 32, rank #766 of 1776 rated models, from 18 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Natural Intelligence | 32.63 | NatInt Score | 79.3 |
| ZeroEval MATH-500 | 97 | MATH-500 Score | 75.8 |
| UGI Leaderboard | 36.95 | UGI Score | 57.7 |
| ZeroEval GPQA Diamond | 76.01 | GPQA Diamond Score | 56.6 |
| BenchTable | 50.9 | Total Score (%) | 54.5 |
| UGI - Writing | 34.61 | Writing Score | 53.9 |
| Chatbot Arena (Text) | 1347 | Elo | 50.3 |
| AI Chess Leaderboard (Reasoning) | 637 | Elo | 44.5 |
| FinanceArena | 41.9 | Overall Accuracy (self-reported) | 36.1 |
| UGI - Willingness (W/10) | 4 | W/10 Score | 29.9 |
| EQ-Bench 3 | 1139.8 | Elo | 24.7 |
| EQ-Bench | 1034.5 | Normalized Elo (self-reported) | 23.7 |
Interactive version: theaggregate.ai/model?slug=llama-3-1-nemotron-ultra-253b-v1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.