Granite 4.0 H Small

Granite 4.0 H Small

IBM · Released Sep 22, 2025
Intelligence #344 / 650
30.3 our score
Speed #243 / 296
47.5 tok/s
Input Price #175 / 688
$0.060 per 1M tokens
Output Price #213 / 688
$0.250 per 1M tokens
Context
Not reported

Analysis Summary

Granite 4.0 H Small is a compact model from IBM with low but measurable reasoning, coding, and instruction-following scores. Pricing is very low, making it viable for high-volume, low-stakes automation rather than demanding analytical work.

Businesses should treat it as a budget utility model for simple classification, extraction, or templated tasks rather than client-facing content or coding projects. It lacks the depth needed for complex reasoning.

Assessed July 29, 2026

Editorial notes

Granite 4.0 H Small offers modest reasoning and coding ability from IBM at a low price point, best suited to simple, cost-sensitive automation.

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

DFO Verdict

Granite 4.0 H Small offers modest reasoning and coding ability from IBM at a low price point, best suited to simple, cost-sensitive automation.

#344 of 650 overall

Benchmark scores

GPQA Diamond 41.6%
HLE 3.7%
MMLU Pro 62.4%
AIME 2025 13.7%
SciCode 20.9%
LiveCodeBench 25.1%
TerminalBench Hard 2.3%
τ²-Bench 17.3%
IFBench 31.5%
LCR 9%

Magenta = intelligence · Ink = technical/agentic · Cyan = content & long-context · Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.

5.2 Intelligence Index·13.7 Math Index

How Granite 4.0 H Small compares

Granite 4.0 H Small ranks #331 of 401 AI models we track for overall intelligence. At $0.06 per million input tokens it is cheaper than 75% of comparable models.

Position in the field
Intelligence: smarter than 47% of models #344
Speed: faster than 18% of models #243
Price: cheaper than 75% of models #175
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Granite 4.0 H Small $0.06 in $0.25 out
Anthropic: Claude Fable 5 $10.00 in $50.00 out
Claude Opus 5 $5.00 in $25.00 out
Anthropic: Claude Opus 4.8 $5.00 in $25.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Intelligence1.6Technical1.2Value7Content2.8
Performance profile

Strongest on value. The pulled-in technical corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

Pricing

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

What would Granite 4.0 H Small cost your business?

Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.

A website chatbot handling around 100 customer conversations a day, a few short messages each.

3,000
One request is one message, email, draft or automation call.
1,200 tokens

Full calculator with 688 models → Price Calculator

DFO AI AUTOMATION

These numbers get smaller with the right architecture.

We route routine calls to cheap models and save Granite 4.0 H Small for the hard ones. Most clients cut their estimate by 60-80%.

Talk to our team

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.

Who created Granite 4.0 H Small?

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

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.