Skip to content
aiqbench

Ibm · model passport

Granite 4 2 3b

granite-4-2-3b
  • Open weights
  • Apache 2.0 licence
  • 3.7B params
  • Released 2026-08-07(HF repo created)
5/27axes covered
Overall · LMArena
1,290#272 of 396
Best percentile
44.8Coding
Cohort standing
37.2median 60.2

What the data says

Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 2.9 pct — Factuality Arena (1,324)

Uneven: 41.9 percentile points between its best and worst axis — 44.8 pct on Coding versus 2.9 pct on Factuality Arena.

  • Coding44.8 pct1,379Verify →
  • Hard prompts34.3 pct1,311Verify →
  • Instruction following34.1 pct1,284Verify →
  • Overall31.6 pct1,290Verify →
  • Factuality Arena2.9 pct1,324Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Run it yourself

Repositoryibm-granite/granite-4.2-3b
Parameters3.7B
ArchitectureGraniteForCausalLM
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ibm-granite/granite-4.2-3b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • granite-4.2-3b stands at 37.2 (raw mean 29.5) — measured on 5 of 27 axes.

    standingtemplateVerify →

  • granite-4.2-3b stands at 37.2 versus a cohort median of 60.2 across 191 models released within 180 days — below the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →