Which is better, Claude Sonnet 4.5 or Granite 4.2 30B?

Refresh Models —Deals —Regulatory —Sources —

Questions this page answers

Which is better, Claude Sonnet 4.5 or Granite 4.2 30B?: Across 11 shared benchmarks, Claude Sonnet 4.5 scores higher on 7 and Granite 4.2 30B on 4. The widest gap is τ³-Bench, where Granite 4.2 30B scores 68 against 19.

Claude Sonnet 4.5 vs Granite 4.2 30B

Across 11 shared benchmarks, Claude Sonnet 4.5 scores higher on 7 and Granite 4.2 30B on 4. The widest gap is τ³-Bench, where Granite 4.2 30B scores 68 against 19.

AnthropicvsIBM11 shared benchmarks7–4 head-to-head

Benchmark	Claude Sonnet 4.5	Granite 4.2 30B
AIME25 no tools	88	89.2
gdpval	40.4	1225
GPQA Diamond	83.4	66.4
LiveCodeBench v6	64	75.8
MMLU-Pro	88.2	77.6
scicode	45	38.8
SWE-bench Multilingual	68	41.9
SWE-bench Pro	43.6	33.3
SWE-bench Verified	82	57
Terminal-Bench 2.1	55.8	29.2
τ³-Bench	19	68

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.