VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

Llama 3.1 Instruct 405B vs Nemotron 3 Super 120B A12B

MetavsNVIDIA26 shared benchmarks917 head-to-head
BenchmarkLlama 3.1 Instruct 405BNemotron 3 Super 120B A12B
AA Agentic Index6.38.8
AA Intelligence8.525.7
AA-LCR24.760.3
AA-Omniscience-17.1-41.5
arc_challenge96.996.1
Artificial Analysis Coding Index14.537.7
critpt03.1
gdpval09.9
GPQA Diamond51.582.7
GSM8K96.890.7
hellaswag89.289
HLE4.222.8
humaneval8980.5
IFBench3972.6
LiveCodeBench30.182.1
MBPP73.481.7
mmlu88.686
MMLU-Pro73.483.8
OmniScience Accuracy23.224.3
OmniScience Non-Hallucination4913
OpenBookQA9448.6
scicode29.942
SWE-bench Verified24.553.7
Terminal-Bench Hard6.828.8
winogrande86.778.9
τ²-Bench Telecom (AA run)1967.8

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.