all the models — AI benchmark observatory
← Models

IBM Granite 4.2 3B

IBM · open weight · granite-4.2-3b

IBM Granite 4.2 3B is the compact 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. Unlike the 8B and 30B, it did not receive the extra agentic RL block. Open weights on Hugging Face under Apache 2.0. Text-only (not multimodal).

AIME 2025MMLU-ProGPQA

Benchmark scores

BenchmarkScore
AIME 20250.78
MMLU-Pro0.68
GPQA0.55

Pricing

  • DeepInfra$0.03 / $0.12

Input / output per 1M tokens

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.
IBM Granite 4.2 3B Benchmarks · all the models