Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
NVIDIALlama开源权重Llama 3.1 Community License
描述
A 253B parameter derivative of Meta Llama 3.1 405B Instruct, developed by NVIDIA using Neural Architecture Search (NAS) and vertical compression. It underwent multi-phase post-training (SFT for Math, Code, Reasoning, Chat, Tool Calling; RL with GRPO) to enhance reasoning and instruction-following. Optimized for accuracy/efficiency tradeoff on NVIDIA GPUs. Supports 128k context.
发布日期
2025-04-07
参数规模
253.0B
上下文长度
128K
支持模态
text
能力雷达图
30
general
64
coding
72
reasoning
53
science
70
agents
0
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Chat
IFEvalGoogle Research (2023)
89.5%自报
General
BFCL v2
74.1%自报
Math
MATH-500
97.0%自报
AIME 2025
72.5%自报
Reasoning
GPQANYU + Cohere + Anthropic (2023)
76.0%自报
LiveCodeBench
66.3%自报
AA 评测指数
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))95.2
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))82.5
Aime(MAA (Mathematical Association of America))74.7
Gpqa(NYU + Cohere + Anthropic (2023))72.8
Livecodebench(UC Berkeley + MIT + Cornell (2024))64.1
Math Index(Artificial Analysis)63.7
Aime 25(MAA (Mathematical Association of America))63.7
Ifbench(Google Research (2023))38.2
Tau2(Sierra + U Toronto + Vector Institute (2025))11.4
Intelligence Index(Artificial Analysis)7.5
Hle(Center for AI Safety + Scale AI (2025))7.4
Terminalbench Hard(Stanford × Laude Institute (2026))2.3
LLM Stats 分类评分
(LLM Stats (zeroeval))Chat90
Instruction Following90
Structured Output90
Math80
Physics80
Reasoning80
General80
Biology80
Chemistry80
Code70
Tool Calling70
定价
输入价格免费
输出价格免费
混合价格(3:1)免费
速度
Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s
供应商价格排行
暂无提供商数据