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-R1 vs DeepSeek-V3.2

DeepSeekvsDeepSeek37 shared benchmarks235 head-to-head
BenchmarkDeepSeek-R1DeepSeek-V3.2
AA Agentic Index3.139.8
AA Intelligence18.632.8
AA-LCR5670.7
AA-Omniscience-31.3-22.5
AIME 202587.593.1
arc_agi_121.257
ARC-AGI-21.34
Artificial Analysis Coding Index24.644.2
browsecomp8.951.4
browsecomp_zh35.765
critpt0.62.9
gdpval1.518.8
GPQA Diamond8184
HLE17.740.8
HMMT 202579.490.2
hmmt_feb_202576.792.5
IFBench3961
LiveCodeBench84.486
longbench_v258.359.8
mmlu_redux93.493.7
MMLU-Pro8586
OmniScience Accuracy30.733
OmniScience Non-Hallucination10.517.3
scicode35.739
simpleqa_verified27.427.5
SWE-bench Multilingual30.570.2
SWE-bench Verified57.673.1
TauBench V3 - Banking6.418.8
Terminal-Bench5.737.7
Terminal-Bench 2.119.146.8
Terminal-Bench Hard6.135.6
vectara_answer_rate9792.6
vectara_avg_summary_length93.562
vectara_factual_consistency88.793.7
vectara_hallucination_rate11.36.3
τ²-Bench Telecom (AA run)11.490.6
τ³-Bench6.469.2

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.