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

Claude Sonnet 4.6 vs DeepSeek-R1

AnthropicvsDeepSeek28 shared benchmarks271 head-to-head
BenchmarkClaude Sonnet 4.6DeepSeek-R1
AA Agentic Index61.63.1
AA Intelligence48.418.6
AA-LCR7456
AA-Omniscience12.2-31.3
arc_agi_186.521.2
ARC-AGI-260.41.3
Artificial Analysis Coding Index6324.6
browsecomp76.28.9
critpt3.10.6
gdpval54.81.5
GPQA Diamond89.981
harmbench24.254.6
HLE4917.7
IFBench56.639
OmniScience Accuracy40.930.7
OmniScience Non-Hallucination51.610.5
scicode4735.7
simpleqa_verified2927.4
SWE-bench Verified79.657.6
TauBench V3 - Banking34.46.4
Terminal-Bench 2.171.219.1
Terminal-Bench Hard59.16.1
vectara_answer_rate99.997
vectara_avg_summary_length114.793.5
vectara_factual_consistency89.488.7
vectara_hallucination_rate10.611.3
τ²-Bench Telecom (AA run)97.911.4
τ³-Bench30.56.4

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.