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 3.7 Sonnet vs DeepSeek-V3

AnthropicvsDeepSeek30 shared benchmarks282 head-to-head
BenchmarkClaude 3.7 SonnetDeepSeek-V3
AA Agentic Index371.6
AA Intelligence27.615.4
AA-LCR62.341.3
AA-Omniscience-0.7-37.6
aider_polyglot64.955.1
AIME 202554.851.3
AIR-Bench 202481.840.8
anthropic_red_team99.797.1
Artificial Analysis Coding Index36.423
bbq92.196.7
critpt0.90
gdpval27.40
GPQA Diamond84.868.4
harmbench84.349.7
HLE9.75.2
hmmt_feb_202531.729.2
IFBench48.341
ifeval93.287.3
math_500_em96.294
mmmlu86.179.4
multichallenge51.631.4
OmniScience Accuracy28.225.4
OmniScience Non-Hallucination6023.3
scicode40.335.8
simple_safety_tests10095.3
simplebench46.427.2
SWE-bench Verified70.342
Terminal-Bench Hard21.215.2
xstest96.497.1
τ²-Bench Telecom (AA run)54.747.1

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.