What is the IQ of Granite 4.2 30B?

Granite 4.2 30B has an estimated IQ of 98, which ranks #118 out of 148 public models on the AI IQ leaderboard. The score combines six equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.

How much does Granite 4.2 30B cost?

Granite 4.2 30B costs $0.16 per million input tokens and $0.65 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.5787 per million input-plus-output tokens.

Is Granite 4.2 30B open source?

Yes — Granite 4.2 30B is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.

When was Granite 4.2 30B released?

Granite 4.2 30B was publicly released on August 25, 2026.

How large is the context window of Granite 4.2 30B?

Granite 4.2 30B supports a context window of 524,288 tokens — the amount of text it can consider in a single request.

How fast is Granite 4.2 30B?

In independent measurements, Granite 4.2 30B generates about 77 tokens per second, with a typical response time of about 33 seconds.

Ibm

Granite 4.2 30B

Public AI IQ model profile with source-backed benchmark results and derived ranking context.

IQ

98

EQ

n/a

Effective Cost

$0.5787

IQ Rank

#118

Granite 4.2 30B API pricing — full price table, workload cost examples, and cheaper alternatives.

Release and Capabilities

Public release	2026-08-25
Modalities	text
Context window	524,288 tokens

Apache 2.0 open weights on Hugging Face, with local deployment through Transformers, vLLM, SGLang, and compatible inference providers

Publisher-reported capabilities

Granite 4.2 30B is IBM's flagship dense reasoning model for complex reasoning, code generation, tool calling, and agentic workflows.
It supports native 128K context with a documented long-context extension to 512K and switchable full, low-effort, and non-thinking modes.

Limitations and availability caveats

IBM says multilingual performance can vary relative to English.
The model may produce inaccurate, biased, or unsafe responses, and IBM recommends deployment alongside additional safety controls.

Official release and model references

Measured Coverage and Estimates

Granite 4.2 30b has 6 of 30 tracked IQ benchmark inputs across 2 of 6 dimensions. Raw benchmark tables contain source-backed results only. Derived IQ combines all six dimensions using the shared scoring methodology, including estimates where direct coverage is incomplete.

Among dimensions with direct benchmark coverage, this profile's highest estimated scores are Academic Reasoning (IQ 107) and Reliability (IQ 104). These dimension estimates can include statistical adjustments or predecessor priors; they are not raw benchmark percentages or claims of real-world task success.

Benchmark versions, evaluation harnesses, and coverage affect comparisons; a missing result is not a score of zero. See the scoring methodology for estimation and uncertainty limits.

IQ Dimensions

Dimension	IQ	Coverage
Abstract Reasoning	91	0/3
Mathematical Reasoning	96	0/5
Academic Reasoning	107	4/6
Programmatic Reasoning	92	0/5
Computer Use	99	0/5
Reliability	104	2/6

Benchmark Results

Benchmark	Score	Dimension
AA Long Context Reasoning v1.1	49	Reliability
AA Omniscience	-12.9167	Reliability
CritPt	0.2857	Academic Reasoning
GPQA Diamond	64.4444	Academic Reasoning
Humanity's Last Exam	11.1677	Academic Reasoning
SciCode	37.8472	Academic Reasoning

Compare

Frequently Asked Questions

What is the IQ of Granite 4.2 30B?: Granite 4.2 30B has an estimated IQ of 98, which ranks #118 out of 148 public models on the AI IQ leaderboard. The score combines six equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
How much does Granite 4.2 30B cost?: Granite 4.2 30B costs $0.16 per million input tokens and $0.65 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.5787 per million input-plus-output tokens.
Is Granite 4.2 30B open source?: Yes — Granite 4.2 30B is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
When was Granite 4.2 30B released?: Granite 4.2 30B was publicly released on August 25, 2026.
How large is the context window of Granite 4.2 30B?: Granite 4.2 30B supports a context window of 524,288 tokens — the amount of text it can consider in a single request.
How fast is Granite 4.2 30B?: In independent measurements, Granite 4.2 30B generates about 77 tokens per second, with a typical response time of about 33 seconds.