Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models790Deals30d240Policy30d70, 15 pendingSources1,102

Granite 4.2 30B

IBMReleased Aug 25, 2026Current

Score basis

Granite 4.2 30B is capable in instruction following; and behind the leaders in factuality, reasoning, and agentic tasks. Too few results yet to rate coding, safety, long context, math, multimodal tasks, or multilingual tasks.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Capable1 capability
  1. Instruction Following−21.7%1 of 3
Limited3 capabilities
  1. Factuality−35.1%2 of 4
  2. Reasoning−45.4%3 of 6
  3. Agentic−46.5%3 of 7
Not rated6 capabilities

Too few results yet to rate Coding, Safety, Long Context, Math, Multimodal or Multilingual.

Price

$0.16input$0.65outputper million tokens

From Artificial Analysis · All prices

Cheaper than 71% of 322 priced models · 3:1 input-to-output blend, log scale

Evidence

38results on33benchmarks

  • 1 independently verified
  • 15 aggregator
  • 22 vendor-reported

From 4 sources · latest Oct 24, 2026 · How verification works

Granite 4.2 30B benchmark results

38 results on 33 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Instruction Following

CapableFull instruction following ranking

21.7% behind the leader1 of 3 ranked benchmarks measured

Factuality

LimitedFull factuality ranking

35.1% behind the leader2 of 4 ranked benchmarks measured

Reasoning

LimitedFull reasoning ranking

45.4% behind the leader3 of 6 ranked benchmarks measured

Show 1 more reasoning resultHide 1 reasoning result

Agentic

LimitedFull agentic ranking

46.5% behind the leader3 of 7 ranked benchmarks measured

Show 1 more agentic resultHide 1 agentic result

Coding

Not enough dataFull coding ranking

0 of 10 ranked benchmarks measured

Show 5 more coding resultsHide 5 coding results

Long Context

Not enough dataFull long context ranking

0 of 3 ranked benchmarks measured

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 12 more resultsHide 12 results

Granite 4.2 30B: common questions

Who makes Granite 4.2 30B?

Granite 4.2 30B is made by IBM.

When was Granite 4.2 30B released?

Granite 4.2 30B was released on Aug 25, 2026, according to Artificial Analysis.

What is Granite 4.2 30B good at?

Granite 4.2 30B is capable in instruction following; and behind the leaders in factuality, reasoning, and agentic tasks. Too few results yet to rate coding, safety, long context, math, multimodal tasks, or multilingual tasks.

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, according to Artificial Analysis. At a mix of three input tokens to one output token, it is cheaper than 71% of the 322 priced models we track.

How many benchmarks has Granite 4.2 30B been tested on?

We track 38 results for Granite 4.2 30B on 33 benchmarks from 4 sources, 1 of them independently verified. The latest was recorded on Oct 24, 2026.

About this record

Where Granite 4.2 30B's numbers come from, and every name it appears under.

Tracked since
Aug 25, 2026
Newest source mention
Aug 28, 2026

Where the results come from

Verification: 38 scores · 1 independently verified · 15 aggregator-attributed · 22 vendor-reported. How these tiers are assigned

From 4 sources on 3 sites. api.llm-stats.com supplies 16 of them; the 1 independently verified result comes from 1 site. Bars are coloured by trust tier.

  • api.llm-stats.com16
  • artificialanalysis.ai16
  • huggingface.co6

Also known as

granite 4.2granite 4.2 30b densegranite-4-2-30bibm-granite/granite-4.2-30b