Skip to content
ModelCap

granite 4.2 30b

Current board #86Arena #216Official publisher releaseOpen weights7d #83 → #86

IBM Granite·ibm-granite/granite-4.2-30b

granite 4.2 30b is ModelCap current-board rank #86 with Index 30.4 (Measured), from the ModelCap Index as of 3 Sept 2026, 02:20 UTC.

granite 4.2 30b has a published context limit of 131K tokens in the ModelCap catalogue as of 3 Sept 2026, 02:20 UTC.

granite 4.2 30b weight access is open weights, from ModelCap classification of published repository metadata as of 3 Sept 2026, 02:20 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · Current board
30.4#86
Measured · 67% support · score interval 30.4–39.8
Evidence as of 2 Sept 2026, 20:11 UTC
Market Gravity
10.0Increased by 0.1
Secondary market signal

OpenRouter endpoint status could not be refreshed. This model is not treated as currently served until a successful observation arrives.

Input
$0.16
per 1M tokens
Output
$0.65
per 1M tokens
Context
131K
tokens
Providers
0
endpoints
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes

Current provider status is unavailable.

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
deepinfra
live
$0.16$0.65131K303 ms84.2 tok/stools

Reported evaluation leads (5)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
harborframework/terminal-bench-2.1
terminalbench_2_1
29.24
Unpinned
not published
Reported
Quarantined
ScaleAI/SWE-bench_Pro
SWE_Bench_Pro
33.29
Unpinned
not published
Reported
Quarantined
SWE-bench/SWE-bench_Multilingual
swe_bench_multilingual_%_resolved
41.89
Unpinned
not published
Reported
Quarantined
SWE-bench/SWE-bench_Verified
swe_bench_%_resolved
57
Unpinned
not published
Reported
Quarantined
TIGER-Lab/MMLU-Pro
mmlu_pro
77.6
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
30.4
Measured · 3 public benchmark observations across 3 boards
Current board
#86
Public rank basis
Measured (measured)
Index support
66.7% · strong
Index interval
30.4–39.8
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
2 Sept 2026, 20:11 UTC
Identity binding
Exact catalogue product · ibm-granite/ibm-granite/granite-4.2-30b · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata ibm-granite/granite-4.2-30b@8b445a5c315f32da0f89e1f648bfec0cd601b154 (not the evaluation revision)
Index observations used
3
Qualified Index evidence point
35.1
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
35.1
Evidence status
confirmed · 78% mass
General preference
35.0
Coding
36.2
Agents & tools
Reasoning
Evidence breadth
92%
Evidence coverage
67%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
Liquidity (providers × uptime)
Open reach (HF downloads)
36.8
Surface (context / tools / modalities)
45.2
Freshness
90.4
  • · HF 30d downloads 4778
  • · Catalogue: context 131072, tools
  • · First seen 2026-08-07

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
78.0
strong · 92% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
100.0
Deployability
48.7
Evaluation provenance
66.8

Missing: deployability.measured-provider-uptime, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
10.0
OpenRouter weekly popularity
Not listed

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
LMArena
Official rank
#216 of 398
Rating
1341.2
95% confidence interval
1331–1352
Votes
3K
Source published at
1 Sept 2026, 00:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
0.0

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
0.0

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
36.8

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
90.4

Time since first public availability, on a six-month half-life.

Specification

Context window
131K tokens
Max output
Inputs
Text
Outputs
Text
Tokenizer
Cached input tokens
Not offered
First seen on OpenRouter
7 Aug 2026

Capabilities

  • Not supported: Reasoning
  • Supported: Tool use
  • Not supported: Structured output
  • Not supported: Response format
  • Not supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
apache-2.0
Pinned revision
8b445a5c315f
Parameters
29.3B
Architecture
GraniteForCausalLM
Model type
granite
Hugging Face downloads (30d)
5K
Downloads (all time)
5K
Likes
105
Repository updated
2 Sept 2026, 22:00 UTC

Compare granite 4.2 30b with

Pick any model

Benchmark leaderboards featuring granite 4.2 30b

All leaderboards
Public benchmark boards on which granite 4.2 30b has a published result
LeaderboardScoreSource rankConfigurationPublished
Arena coding leaderboardArena (LMArena)13961374–1417#197 of 393Default1 Sept 2026
Artificial Analysis Intelligence IndexArtificial Analysis23.7#238 of 623intelligence-index2 Sept 2026
Terminal-Bench 2.1 (Artificial Analysis run)Artificial Analysis26.6%#154 of 226terminal-bench-2.12 Sept 2026
Humanity's Last Exam (Artificial Analysis run)Artificial Analysis11.2%#240 of 591humanitys-last-exam2 Sept 2026

Alternatives to granite 4.2 30b, by the numbers

Ranked neighbours

Models within 3 places of #86 on the ModelCap Index.

Other ranked IBM Granite models

The same publisher's other current models with a public Index position.

granite 4.2 30b: common questions

How does granite 4.2 30b rank among AI models?

granite 4.2 30b holds ModelCap Index position #86 of 225 ranked language models as of 3 September 2026, with an Index score of 30.4 (interval 30.4–39.8); evidence: measured. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.

How much does granite 4.2 30b cost per 1M tokens?

No live API price is listed for granite 4.2 30b in the current snapshot as of 3 September 2026 because the latest endpoint refresh was unavailable. ModelCap shows a price only when a provider currently lists one.

What is the context window of granite 4.2 30b?

granite 4.2 30b has a published context window of 131K tokens (131,072). Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.

Is granite 4.2 30b open-weight?

Open weights (apache-2.0). Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI. The repository is ibm-granite/granite-4.2-30b on Hugging Face.

Which benchmarks has granite 4.2 30b been evaluated on?

granite 4.2 30b has published results on 4 public boards tracked by ModelCap as of 3 September 2026: Arena coding 1396 (#197 of 393), AA Intelligence Index 23.7 (#238 of 623), AA Terminal-Bench 2.1 26.6% (#154 of 226) and AA Humanity's Last Exam 11.2% (#240 of 591). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.

How does granite 4.2 30b compare with Mercury 2?

granite 4.2 30b ranks #86 (Index 30.4) and Mercury 2 ranks #85 (Index 30.8) on the ModelCap Index as of 3 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.

When was granite 4.2 30b released?

granite 4.2 30b first appeared in the catalogue on 7 Aug 2026. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.