all the models — AI benchmark observatory
← Models

IBM Granite 4.2 30B

IBM · open weight · granite-4.2-30b

IBM Granite 4.2 30B is the flagship dense decoder-only reasoning LLM in the Granite 4.2 family. It supports native think, non-think, and low-effort modes, tool calling, and a 128K native context window with extension to 512K. The 8B and 30B sizes received additional agentic reinforcement learning for multi-step tool use. Open weights on Hugging Face under Apache 2.0. Text-only (not multimodal).

AIME 2025HMMT25MMLU-ProGPQASWE-Bench Ve

Benchmark scores

BenchmarkScore
AIME 20250.89
HMMT250.89
MMLU-Pro0.78
GPQA0.66
SWE-Bench Verified0.57

Pricing

  • DeepInfra$0.16 / $0.65

Input / output per 1M tokens

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.
IBM Granite 4.2 30B Benchmarks · all the models