Llama 3.1 Nemotron Instruct 70B
NVIDIALlamaOpen WeightLlama 3.1 Community License
Description
A large language model customized by NVIDIA to improve the helpfulness of LLM generated responses. It is a fine-tuned version of Llama 3.1 70B Instruct. The model was trained using RLHF (REINFORCE) with HelpSteer2-Preference prompts.
Date de sortie
2024-10-15
Paramètres
70.0B
Longueur du contexte
128K
Modalités
text
Radar de capacités
25
general
17
coding
27
reasoning
33
science
24
agents
0
multimodal
Classements
| Domaine | #Rang | Score | Source |
|---|---|---|---|
| Classement codage | 576 | 11.0 | AA |
| Classement général | 502 | 28.0 | AA |
| Science | 530 | 24.0 | AA |
Scores de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Chat
MT-Bench
0.09 / 100Aut.
General
MMLU
80.2%Aut.
Instruct HumanEval
73.8%Aut.
TruthfulQA
58.6%Aut.
Language
MMLU Chat
80.6%Aut.
Math
GSM8k
91.4%Aut.
GSM8K Chat
81.9%Aut.
Reasoning
HellaSwagAI2 (2019)
85.6%Aut.
Winogrande
84.5%Aut.
ARC-C
69.2%Aut.
Summarization
XLSum English
31.6%Aut.
Indices d'évaluation AA
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))73.3
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))69.0
Gpqa(NYU + Cohere + Anthropic (2023))46.5
Ifbench(Google Research (2023))30.7
Aime(MAA (Mathematical Association of America))24.7
Tau2(Sierra + U Toronto + Vector Institute (2025))23.1
Livecodebench(UC Berkeley + MIT + Cornell (2024))16.9
Math Index(Artificial Analysis)11.0
Aime 25(MAA (Mathematical Association of America))11.0
Lcr(Artificial Analysis)8.3
Intelligence Index(Artificial Analysis)6.9
Terminalbench Hard(Stanford × Laude Institute (2026))4.5
Hle(Center for AI Safety + Scale AI (2025))4.2
Scores par catégorie LLM Stats
(LLM Stats (zeroeval))Math90
Language80
Legal70
Reasoning70
Finance70
General70
Healthcare70
Chat10
Roleplay10
Communication10
Creativity10
Tarification
Prix d'entréeGratuit
Prix de sortieGratuit
Prix mixte (3:1)Gratuit
Vitesse
Tokens/sec0.0
Délai du premier token0.00s
Temps de réponse0.00s
Classement des Prix par Fournisseur
Aucune donnée de fournisseur disponible