Refresh Models —Deals —Regulatory —Sources —

Claude 3.7 Sonnet vs IBM Granite 4.0 Small

6 SHARED BENCHMARKS

Across 6 shared benchmarks, Claude 3.7 Sonnet scores higher on 3 and IBM Granite 4.0 Small on 2, with 1 level. The widest gap is xstest, where Claude 3.7 Sonnet scores 96.4 against 80.6.

ANTHROPICVSIBM6 SHARED3–2 HEAD-TO-HEAD

BenchmarkClaude 3.7 SonnetMARGINIBM Granite 4.0 Small

AIR-Bench 202481.880.4

anthropic_red_team99.799.8

bbq92.190

harmbench84.386.4

simple_safety_tests100100

xstest96.480.6

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.