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 o4-mini

DeepSeekvsOpenAI25 shared benchmarks232 head-to-head
BenchmarkDeepSeek-V4-Proo4-mini
AA Agentic Index63.336.1
AA Intelligence5326.1
AA-LCR7060
AA-Omniscience-10.6-35.7
Artificial Analysis Coding Index59.425.6
browsecomp83.451.5
critpt130.6
gdpval4925.4
GPQA Diamond90.581.4
HLE48.216.5
IFBench76.568.7
LiveCodeBench93.584.5
OmniScience Accuracy4324.8
OmniScience Non-Hallucination12.219.5
scicode5046.5
simplebench50.938.7
simpleqa_verified57.923.9
strongreject98.696
SWE-bench Verified80.668.1
Terminal-Bench Hard46.215.2
vectara_answer_rate97.299.2
vectara_avg_summary_length153.8130.9
vectara_factual_consistency91.481.4
vectara_hallucination_rate8.618.6
τ²-Bench Telecom (AA run)96.255.6

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.