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 vs Claude Sonnet 5

AnthropicvsAnthropic22 shared benchmarks121 head-to-head
BenchmarkClaude Sonnet 4Claude Sonnet 5
AA Agentic Index39.249.7
AA Intelligence29.855.3
AA-LCR69.777
AA-Omniscience0.216.4
Artificial Analysis Coding Index37.671.5
browsecomp12.284.7
critpt1.116.9
gdpval31.254.8
GPQA Diamond7891.1
HLE10.757.4
MMMU-Pro62.477.3
OmniScience Accuracy22.740
OmniScience Non-Hallucination70.960.6
OSWorld-Verified42.281.2
scicode4053.6
simplebench45.560.6
SWE-bench Multilingual56.978.3
SWE-bench Pro42.763.2
SWE-bench Verified80.285.2
TauBench V3 - Banking16.737.3
Terminal-Bench 2.136.380.5
τ³-Bench13.828.2

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.