Granite 4.0 H 350M

by IBM

Released

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Intelligence Index1.0
Math Index1.3
Reasoning & knowledge
MMLU-Pro
13%
GPQA Diamond
26%
Humanity's Last Exam
6%
Long-context reasoning
0%
Coding
LiveCodeBench
2%
SciCode
2%
Agentic & tool use
Terminal-Bench Hard
0%
τ²-Bench Telecom
15%
Math & instruction following
AIME 2025
1%
IFBench
18%

Available routes

No routes currently available — Granite 4.0 H 350M isn't routed through the Opper gateway right now. It's tracked here for its release history.

Contact us about this model →

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Granite 4.0 H 350M — release date & benchmarks | Opper AI