Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)
NVIDIALlama오픈 웨이트Llama 3.1 Community License
설명
Llama-3.3-Nemotron-Super-49B-v1 is a large language model (LLM) derived from Meta Llama-3.3-70B-Instruct. It's post-trained for reasoning, chat, RAG, and tool calling, offering a balance between accuracy and efficiency (optimized for single H100). It underwent multi-phase post-training including SFT and RL (RLOO, RPO).
출시일
2025-03-18
파라미터
49.9B
컨텍스트 길이
131K
모달리티
text
능력 레이더
26
general
28
coding
25
reasoning
37
science
70
agents
0
multimodal
랭킹
벤치마크 점수 (LLM Stats)
(LLM Stats (zeroeval))Chat
MT-Bench
0.92 / 100자체 보고
General
Arena Hard
88.3%자체 보고
BFCL v2
73.7%자체 보고
Math
MATH-500
96.6%자체 보고
AIME 2025
58.4%자체 보고
Reasoning
MBPP
0.91 / 100자체 보고
GPQANYU + Cohere + Anthropic (2023)
66.7%자체 보고
AA 평가 지수
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))77.5
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))69.8
Gpqa(NYU + Cohere + Anthropic (2023))51.7
Ifbench(Google Research (2023))39.5
Livecodebench(UC Berkeley + MIT + Cornell (2024))28.0
Aime(MAA (Mathematical Association of America))19.3
Lcr(Artificial Analysis)12.0
Math Index(Artificial Analysis)7.7
Aime 25(MAA (Mathematical Association of America))7.7
Intelligence Index(Artificial Analysis)7.3
Hle(Center for AI Safety + Scale AI (2025))3.8
Terminalbench Hard(Stanford × Laude Institute (2026))0.0
LLM Stats 카테고리 점수
(LLM Stats (zeroeval))Chat90
Roleplay90
Communication90
Creativity90
Writing90
Math80
Reasoning80
General80
Physics70
Biology70
Chemistry70
Tool Calling70
가격
입력 가격무료
출력 가격무료
혼합 가격 (3:1)무료
속도
토큰/초0.0
첫 토큰 지연0.00s
첫 응답 지연0.00s
공급자 가격 순위
프로바이더 데이터가 없습니다