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 Gemma 4 E2B

AnthropicvsGoogle24 shared benchmarks240 head-to-head
BenchmarkClaude Sonnet 4Gemma 4 E2B
AA Agentic Index39.27.4
AA Intelligence29.810
AA-LCR69.717
AA-Omniscience0.2-23.6
Artificial Analysis Coding Index37.68.3
critpt1.10
gdpval31.20
GPQA Diamond7843.4
HLE10.74.8
IFBench5538
ifeval87.682.9
LiveCodeBench v648.544
MMLU-Pro8460
mmmlu86.567.4
MMMU-Pro62.444.6
OmniScience Accuracy22.78.2
OmniScience Non-Hallucination70.967.6
scicode4020.9
Tau2 retail7518.9
TauBench V3 - Banking16.74.5
Terminal-Bench 2.136.30.4
Terminal-Bench Hard31.13
τ²-Bench6524.5
τ²-Bench Telecom (AA run)64.622.2

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.