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

DeepSeek-V4-Pro vs Llama 3.1 Instruct 405B

DeepSeekvsMeta23 shared benchmarks221 head-to-head
BenchmarkDeepSeek-V4-ProLlama 3.1 Instruct 405B
AA Agentic Index63.36.3
AA Intelligence538.5
AA-LCR7024.7
AA-Omniscience-10.6-17.1
Artificial Analysis Coding Index59.414.5
Chinese SimpleQA (C-SimpleQA)77.754.7
Codeforces320625.3
critpt130
gdpval490
GPQA Diamond90.551.5
HLE48.24.2
IFBench76.539
LiveCodeBench93.530.1
MMLU-Pro87.573.4
OmniScience Accuracy4323.2
OmniScience Non-Hallucination12.249
scicode5029.9
simplebench50.923
simpleqa57.923.2
SWE-bench Pro55.411.2
SWE-bench Verified80.624.5
Terminal-Bench Hard46.26.8
τ²-Bench Telecom (AA run)96.219

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.