← 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).
Benchmark scores
| Benchmark | Score |
|---|---|
| AIME 2025 | 0.89 |
| HMMT25 | 0.89 |
| MMLU-Pro | 0.78 |
| GPQA | 0.66 |
| SWE-Bench Verified | 0.57 |
Pricing
- DeepInfra$0.16 / $0.65
Input / output per 1M tokens
AA metrics
No Artificial Analysis link yet.
Arena Elo
- No Arena snapshot linked.
