Granite 4.0 H Small

Granite 4.0 H Small

IBM · Released Sep 22, 2025 Professional
Intelligence #10 / 576
82.0 Our Score
Speed #2 / 271
480.4 tokens / sec
Input #165 / 577
$0.060 per 1M tokens
Output #200 / 577
$0.250 per 1M tokens
Context
— Not reported

Analysis Summary

Granite 4.0 H Small is IBM's compact hybrid model in the Granite 4.0 family, priced at $0.06 per million input tokens and $0.25 output, making it one of the more affordable options with pricing data. MMLU Pro at 0.624 and GPQA at 0.416 show reasonable general knowledge for its size class, and livecodebench at 0.251 indicates some coding capability.

However, the intelligence index of 10.8 and coding index of 8.5 place it well below the threshold for professional coding or complex reasoning tasks. Agentic performance at 9.8 and long-context reliability at 0.09 are both weak, limiting its usefulness for document analysis or multi-step automation.

At its price point, Granite 4.0 H Small may suit high-volume, low-complexity tasks such as classification, simple Q&A, or lightweight content formatting where cost is the primary constraint. It is not a fit for coding, agent orchestration, or any task requiring sustained reasoning.

Assessed June 6, 2026

Editorial notes

Granite 4.0 H Small from IBM offers moderate general knowledge and reasonable coding for a small model at $0.06 input, but intelligence and agentic scores are too limited for most professional business workflows.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence2.2Technical1.3Value7Content2.3
Intelligence 2.2/10
Technical 1.3/10
Content 2.3/10
Value 7/10

How Granite 4.0 H Small compares

Granite 4.0 H Small ranks #300 of 378 AI models we track for overall intelligence, #253 of 315 for coding, #259 of 289 for agentic tasks. At $0.06 per million input tokens it is cheaper than 71% of comparable models.

Performance Indices

Source: Artificial Analysis

10.8 Intelligence Index
8.5 Coding Index
9.8 Agentic Index
13.7 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 41.6% Graduate-level scientific reasoning
HLE 3.7% Humanity's Last Exam
MMLU Pro 62.4% Multi-task language understanding
AIME 2025 13.7% Competition mathematics (2025)
SciCode 20.9% Scientific computing

Technical

LiveCodeBench 25.1% Live coding evaluation
TerminalBench Hard 2.3% Agentic terminal tasks
τ²-Bench 17.3% Conversational agent benchmark

Content

IFBench 31.5% Instruction following
LCR 9% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does Granite 4.0 H Small stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

ProviderIBM
Release Date September 22, 2025
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.06 $0.000060
Output $0.25 $0.000250

Frequently asked questions about Granite 4.0 H Small

How much does Granite 4.0 H Small cost?

Granite 4.0 H Small costs $0.06 per million input tokens and $0.25 per million output tokens.

Is Granite 4.0 H Small good for coding?

On our coding benchmark index, Granite 4.0 H Small ranks #253 of 315 models, placing it in the broader range of the field for code generation and debugging.

Who created Granite 4.0 H Small?

Granite 4.0 H Small is developed by IBM and was released on September 22, 2025.