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 3.5 Sonnet vs Gemma 4 26B A4B

AnthropicvsGoogle25 shared benchmarks520 head-to-head
BenchmarkClaude 3.5 SonnetGemma 4 26B A4B
AA Intelligence1026.1
AI2D94.788.3
AIME 20257.490
arena_vision11461238
Artificial Analysis Coding Index30.239.3
C-Eval76.782.5
GPQA Diamond67.282.3
GSM8K96.977
HLE3.919.3
hmmt_feb_20251.791.7
humaneval93.750
ifeval90.196.4
LiveCodeBench32.879.8
LiveCodeBench v637.277.1
MathVista67.779.4
mmlu88.377.8
mmlu_redux88.992.7
MMLU-Pro7885.2
MMMU7278.4
MMMU-Pro54.773.8
OpenBookQA97.248.8
RealWorldQA60.172.2
scicode36.640.3
supergpqa48.261.4
SWE-bench Verified50.857.4

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.