granite 4.1 8b

Arena #286Official publisher releaseOpen weights

IBM Granite·#370 of 504 in the all-versions archive

granite 4.1 8b is a language model from IBM Granite. It ranks #370 of 504 in ModelCap's all-versions archive, with an Index score of 27.8, measured on 2 public benchmarks. Its score range of 21.8–33.8 spans positions #329–#407. Its weights are openly downloadable.

Figures as of 6 Nov 2026, 20:49 UTC · download the public dataset · methodology

ModelCap Index · All-versions archive

27.8#370

Measured on 2 public benchmarks · range 21.8–33.8

Evidence as of 28 Oct 2026, 00:00 UTC

Market Gravity

15.4

Secondary market signal

Superseded by Granite 4.2 8B. It no longer holds a current-board position; its all-versions archive rank is #370.

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

Input

Self-hosted

weights only · no listed API price

Output

Self-hosted

weights only · no listed API price

Context

—

tokens

Providers

endpoints

Providers

Uptime measured over the last 30 minutes

Current provider status is unavailable.

Reported evaluation leads (4)

Not independent measurement

Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. They remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / task	Metric	Value	Revision	Provenance
Idavidrein/gpqa diamond	—	41.96	Unpinned `not published`	Reported Quarantined
LiquidAI/ifstruct-v1.0 ifstruct_v1	—	68.45	Unpinned `not published`	Reported Quarantined
openai/gsm8k gsm8k	—	92.49	Unpinned `not published`	Reported Quarantined
TIGER-Lab/MMLU-Pro mmlu_pro	—	55.99	Unpinned `not published`	Reported Quarantined

Other versions (1)

Granite 4.2 8BLanguage board #2572 months ago

ModelCap Index · All-versions archive

Methodology

27.8

Measured on 2 public benchmarks

All-versions archive

#370 of 504

Score range: 21.8–33.8
Rank range: #329–#407
Evidence as of: 28 Oct 2026, 00:00 UTC
Benchmarks used: Arena Coding, Arena Overall

Technical details

Public rank basis: Measured (measured)
Evidence label: Measured · 2 public benchmark observations across 2 boards
Index support: 49.7% · moderate
Identity binding: Exact catalogue product · ibm-granite/ibm-granite/granite-4.1-8b · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata ibm-granite/granite-4.1-8b@1504002f650e656a0a3789d99574df12e3e94ed0 (not the evaluation revision)
Index observations used: 2
Qualified Index evidence point: 27.8

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: 27.8
Evidence status: confirmed · 73% mass
General preference: 27.4
Coding: 30.6
Agents & tools: —
Reasoning: —
Evidence breadth: 92%
Evidence coverage: 50%

Market and catalogue signals · secondary, never the language Index rank

Usage (OpenRouter popularity): —
Liquidity (providers × uptime): —
Open reach (HF downloads): 88.0
Surface (context / tools / modalities): 0.0
Freshness: 44.2

· HF 30d downloads 98312
· Catalogue surface
· First seen 2026-04-06

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

Arena Overall27.4
Arena Coding30.6

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

57.7

partial · 70% metadata coverage

Not capability

Artifact reproducibility: 85.0
Access & legal clarity: 100.0
Deployability: 8.0
Evaluation provenance: 48.8

Not yet published: the base model it derives from, a current serving provider, measured provider uptime, published provider pricing, declared context and output limits, pinned evaluation dataset versions.

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

Market activity

Venue coverage

Market Gravity: 15.4
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: #286 of 419
Rating: 1304.0
95% confidence interval: 1294–1314
Votes: 4K
Source published at: 28 Oct 2026, 00:00 UTC
Category: overall
Identity match confidence: 100%

Market Gravity breakdown

Usage55%: 0.0
Liquidity25%: 0.0
Open reach15%: 88.0
Freshness5%: 44.2

Specification

Model ID: ibm-granite/granite-4.1-8b
Declared output cap: Unknown
OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. OpenRouter metadata
Inputs: Text
Outputs: Text
Cached input tokens: Not offered
First seen on OpenRouter: 6 Apr 2026

Capabilities

Not supported: Reasoning
Not 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: 1504002f650e
Parameters: 8.8B
Architecture: GraniteForCausalLM
Model type: granite
Hugging Face downloads (30d): 98K
Downloads (all time): 6.2M
Likes: 257
Repository: ibm-granite/granite-4.1-8b
Repository updated: 4 May 2026, 17:36 UTC

Benchmark leaderboards featuring granite 4.1 8b

All leaderboards

Public benchmark boards on which granite 4.1 8b has a published result
Leaderboard	Score	Source rank	Configuration	Published
Arena text leaderboardArena (LMArena)	13041294–1314	#286 of 419	Not reported	28 Oct 2026
Arena coding leaderboardArena (LMArena)	13531333–1373	#271 of 414	Default	28 Oct 2026

granite 4.1 8b: common questions

How does granite 4.1 8b rank among AI models?

granite 4.1 8b is a superseded version and is not on the current board as of 6 November 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.

How much does granite 4.1 8b cost per 1M tokens?

No live API price is listed for granite 4.1 8b in the current snapshot as of 6 November 2026 because the latest endpoint refresh was unavailable. ModelCap shows a price only when a provider currently lists one.

Is granite 4.1 8b 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-4.1-8b on Hugging Face.

Which benchmarks has granite 4.1 8b been evaluated on?

granite 4.1 8b has published results on 2 public boards tracked by ModelCap as of 6 November 2026: Arena text 1304 (#286 of 419) and Arena coding 1353 (#271 of 414). Each board page ranks every tracked model on that benchmark. The ModelCap Index scores the results its methodology admits, with published uncertainty, and shows reference boards without scoring them.

When was granite 4.1 8b released?

granite 4.1 8b first appeared in the catalogue on 6 Apr 2026. It has since been superseded by Granite 4.2 8B. Rank and price movements since then are recorded on the site's changes feed.