Granite-4.0-H-1B Benchmark Scores & Performance

BenchLM is tracking Granite-4.0-H-1B by IBM. Some benchmark data is visible, but not enough non-generated coverage is available for a leaderboard rank yet.

BenchLM is tracking Granite-4.0-H-1B, but this profile is currently excluded from the public leaderboard because it still lacks enough verified benchmark coverage to rank safely. Only verified public benchmark rows appear below.

Granite-4.0-H-1B is a open weight model with a 128K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

Granite-4.0-H-1B sits inside the Granite 4.0 1B family alongside Granite-4.0-1B. This profile currently has 7 of 62 tracked benchmarks. BenchLM only exposes verified benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Instruction Following (#76), while its weakest is Multilingual (#94). This performance profile makes it a well-rounded choice across a range of tasks.

Provider

IBM

Source Type

Open Weight

Reasoning

Non-Reasoning

Context Window

128K

Model Status

Current

Release Date

Oct 28, 2025

Overall Score

Unranked

Pricing

$0.00 / $0.00

Input / output per 1M

Runtime

N/A

Latency unavailable

Family & Lineage

Family

Granite 4.0 1B

Hybrid

Sibling Models

Rankings Overview

BenchLM is still missing enough verified benchmark coverage to rank this model across the public leaderboard. Only verified public benchmark rows are shown below.

Knowledge Benchmarks

MMLUStaleSaturatedDisplay onlyDetails
59.4%

MMLU · Static refresh · updated March 31, 2026

GPQARefreshingDetails
29.9%

GPQA Diamond · Static refresh · updated March 31, 2026

MMLU-ProRefreshingDetails
34.0%

MMLU-Pro · Static refresh · updated March 31, 2026

Coding Benchmarks

HumanEvalStaleSaturatedDisplay onlyDetails
74%

HumanEval · Static refresh · updated March 31, 2026

Reasoning Benchmarks

BBHStaleSaturatedDisplay onlyDetails
60.4%

BBH 2022 · Static refresh · updated March 31, 2026

Instruction Following Benchmarks

IFEvalStaleDetails
77.4%

IFEval 2023 · Static refresh · updated March 31, 2026

Multilingual Benchmarks

MGSMStaleDetails
37.8%

MGSM 2022 · Static refresh · updated March 31, 2026

Frequently Asked Questions

How does Granite-4.0-H-1B perform overall in AI benchmarks?

Granite-4.0-H-1B has 7 verified benchmark scores on BenchLM, but it does not yet have enough coverage to receive a global overall rank.

Is Granite-4.0-H-1B good for knowledge and understanding?

Granite-4.0-H-1B has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is Granite-4.0-H-1B good for coding and programming?

Granite-4.0-H-1B has visible benchmark coverage in coding and programming, but BenchLM does not currently assign it a global category rank there.

Is Granite-4.0-H-1B good for reasoning and logic?

Granite-4.0-H-1B has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is Granite-4.0-H-1B good for instruction following?

Granite-4.0-H-1B ranks #76 out of 97 models in instruction following benchmarks with an average score of 77.4. There are stronger options in this category.

Is Granite-4.0-H-1B good for multilingual tasks?

Granite-4.0-H-1B ranks #94 out of 97 models in multilingual tasks benchmarks with an average score of 37.8. There are stronger options in this category.

Is Granite-4.0-H-1B open source?

Yes, Granite-4.0-H-1B is an open weight model created by IBM, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Which sibling models are related to Granite-4.0-H-1B?

Granite-4.0-H-1B belongs to the Granite 4.0 1B family. Related variants on BenchLM include Granite-4.0-1B.

Does Granite-4.0-H-1B have full benchmark coverage on BenchLM?

Not yet. Granite-4.0-H-1B currently has 7 verified benchmark scores out of the 62 benchmarks BenchLM tracks. BenchLM only exposes verified public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Granite-4.0-H-1B?

Granite-4.0-H-1B has a context window of 128K, which determines how much text it can process in a single interaction.

Last updated: March 31, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Weekly LLM Updates

New model releases, benchmark scores, and leaderboard changes. Every Friday.

Free. Your signup is stored with a derived country code for compliance routing.