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 Opus 4.7 vs DeepSeek-R1

AnthropicvsDeepSeek30 shared benchmarks273 head-to-head
BenchmarkClaude Opus 4.7DeepSeek-R1
AA Agentic Index64.63.1
AA Intelligence5518.6
AA-LCR75.356
AA-Omniscience27.3-31.3
arc_agi_19221.2
ARC-AGI-275.81.3
Artificial Analysis Coding Index73.624.6
browsecomp79.88.9
critpt120.6
gdpval58.61.5
GPQA Diamond94.281
harmbench17.554.6
HLE54.717.7
IFBench58.639
OmniScience Accuracy48.930.7
OmniScience Non-Hallucination57.710.5
scicode54.535.7
simplebench61.740.8
simpleqa_verified50.627.4
SWE-bench Multilingual80.530.5
SWE-bench Verified87.657.6
TauBench V3 - Banking34.66.4
Terminal-Bench 2.183.119.1
Terminal-Bench Hard54.56.1
vectara_answer_rate9897
vectara_avg_summary_length149.193.5
vectara_factual_consistency8888.7
vectara_hallucination_rate1211.3
τ²-Bench Telecom (AA run)88.611.4
τ³-Bench28.96.4

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.