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 Gemini 3.5 Flash

AnthropicvsGoogle26 shared benchmarks125 head-to-head
BenchmarkClaude Sonnet 4Gemini 3.5 Flash
AA Agentic Index39.270.4
AA Intelligence29.852
AA-LCR69.781
AA-Omniscience0.221.2
arc_agi_163.792.5
ARC-AGI-213.672.1
Artificial Analysis Coding Index37.670.1
critpt1.113.1
frontiermath_tier_4014.6
gdpval31.257.8
GPQA Diamond7892.2
HLE10.742.7
IFBench5576.3
livebench74.875
MMMU-Pro62.484.3
OmniScience Accuracy22.751.4
OmniScience Non-Hallucination70.938.2
OSWorld-Verified42.278.4
scicode4053.1
simplebench45.576.7
SWE-bench Pro42.755.1
TauBench V3 - Banking16.732.2
Terminal-Bench 2.136.378.7
Terminal-Bench Hard31.146.2
τ²-Bench Telecom (AA run)64.695.6
τ³-Bench13.825.4

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.