Skip to content
ModelCap

granite 3.0 8b instruct

Arena #359Official publisher releaseOpen weights

IBM Granite·#472 of 504 in the all-versions archive

granite 3.0 8b instruct is a language model from IBM Granite. It ranks #472 of 504 in ModelCap's all-versions archive, with an Index score of 10.6, measured on 2 public benchmarks. Its score range of 4.8–16.4 spans positions #428–#496. Its weights are openly downloadable.

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

ModelCap Index · All-versions archive
10.6#472
Measured on 2 public benchmarks · range 4.8–16.4
Evidence as of 28 Oct 2026, 00:00 UTC
Market Gravity
11.7
Secondary market signal

Superseded by granite 3.3 8b instruct. It no longer holds a current-board position; its all-versions archive rank is #472.

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
0
endpoints

ModelCap Index · All-versions archive

Methodology
10.6
Measured on 2 public benchmarks
All-versions archive
#472 of 504
Score range
4.8–16.4
Rank range
#428–#496
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
52.5% · moderate
Identity binding
Exact catalogue product · ibm-granite/ibm-granite/granite-3.0-8b-instruct · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata ibm-granite/granite-3.0-8b-instruct@5af56291a1c6ca9056df597aab0cff53edabddb0 (not the evaluation revision)
Index observations used
2
Qualified Index evidence point
10.6
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
10.6
Evidence status
confirmed · 74% mass
General preference
10.3
Coding
12.8
Agents & tools
—
Reasoning
—
Evidence breadth
92%
Evidence coverage
53%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
—
Liquidity (providers × uptime)
—
Open reach (HF downloads)
76.2
Surface (context / tools / modalities)
0.0
Freshness
5.4
  • · HF 30d downloads 13093
  • · Catalogue surface
  • · First seen 2024-10-02

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
62.2
partial · 74% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
100.0
Deployability
8.0
Evaluation provenance
49.1

Not yet published: 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
11.7
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
#359 of 419
Rating
1183.2
95% confidence interval
1175–1192
Votes
7K
Source published at
28 Oct 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%
76.2

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

Freshness5%
5.4

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

Specification

Model ID
ibm-granite/granite-3.0-8b-instruct
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
2 Oct 2024

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
5af56291a1c6
Parameters
8.2B
Architecture
GraniteForCausalLM
Model type
granite
Hugging Face downloads (30d)
13K
Downloads (all time)
1.1M
Likes
209
Repository updated
19 Dec 2024, 19:44 UTC

Benchmark leaderboards featuring granite 3.0 8b instruct

All leaderboards
Public benchmark boards on which granite 3.0 8b instruct has a published result
LeaderboardScoreSource rankConfigurationPublished
Arena text leaderboardArena (LMArena)11831175–1192#359 of 419Not reported28 Oct 2026
Arena coding leaderboardArena (LMArena)12401223–1258#351 of 414Default28 Oct 2026

granite 3.0 8b instruct: common questions

How does granite 3.0 8b instruct rank among AI models?

granite 3.0 8b instruct 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 3.0 8b instruct cost per 1M tokens?

No live API price is listed for granite 3.0 8b instruct 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 3.0 8b instruct 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-3.0-8b-instruct on Hugging Face.

Which benchmarks has granite 3.0 8b instruct been evaluated on?

granite 3.0 8b instruct has published results on 2 public boards tracked by ModelCap as of 6 November 2026: Arena text 1183 (#359 of 419) and Arena coding 1240 (#351 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 3.0 8b instruct released?

granite 3.0 8b instruct first appeared in the catalogue on 2 Oct 2024. It has since been superseded by granite 3.3 8b instruct. Rank and price movements since then are recorded on the site's changes feed.