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 Gemini 3 Pro

DeepSeekvsGoogle36 shared benchmarks531 head-to-head
BenchmarkDeepSeek-R1Gemini 3 Pro
AA Agentic Index3.152
AA Intelligence18.640.6
AA-LCR5673
AA-Omniscience-31.315.3
AIME 202587.5100
arc_agi_121.275
ARC-AGI-21.354
Artificial Analysis Coding Index24.646.5
browsecomp8.959.2
browsecomp_zh35.766.8
critpt0.69.1
Fortress74.441.7
gdpval1.534.2
GPQA Diamond8191.9
HLE17.745.8
hmmt_feb_202576.797.5
IFBench3970.4
LiveCodeBench84.492
longbench_v258.368.2
MMLU-Pro8590.1
multichallenge4565.7
MultiNRC27.659
OmniScience Accuracy30.755.8
OmniScience Non-Hallucination10.510
scicode35.756.1
simplebench40.876.4
simpleqa92.372.1
simpleqa_verified27.472.9
SWE-bench Multilingual30.568.7
SWE-bench Verified57.678
Terminal-Bench Hard6.156.9
vectara_answer_rate9799.4
vectara_avg_summary_length93.5101.9
vectara_factual_consistency88.786.4
vectara_hallucination_rate11.313.6
τ²-Bench Telecom (AA run)11.498

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.