Ibm · model passport
Granite 4 1 8b
granite-4-1-8b- Open weights
- Apache 2.0 licence
- 8.8B params
- Released 2026-04-06(HF repo created)
- Overall · LMArena
- 1,304#263 of 396
- Best percentile
- 37.4Hard prompts
- Cohort standing
- 33.6median 62.7
What the data says
Benchmarked on 7 of 27 tracked axes. Every figure below is the model's own published result on that board.
Weakest axes
- 1.7 pct — Factuality Arena (1,311)
- 5 pct — WebDev Arena (1,193)
Uneven: 35.7 percentile points between its best and worst axis — 37.4 pct on Hard prompts versus 1.7 pct on Factuality Arena.
- Hard prompts37.4 pct1,320Verify →
- Coding36.8 pct1,353Verify →
- IFBench (Artificial Analysis)36.7 pct38.6%Verify →
- Instruction following34.8 pct1,289Verify →
- Overall33.8 pct1,304Verify →
- WebDev Arena5 pct1,193Verify →
- Factuality Arena1.7 pct1,311Verify →
- 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
- 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
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "ibm-granite/granite-4.1-8b"
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-4.1-8b stands at 33.6 (raw mean 26.6) — measured on 7 of 27 axes.
granite-4.1-8b stands at 33.6 versus a cohort median of 62.7 across 116 models released within 180 days — below the peer median.
granite-4.1-8b scores at percentile 1.7 on Factuality Arena.
granite-4.1-8b scores in the 5th percentile on WebDev Arena.
granite-4.1-8b ranks between #150 and #978 across 6 built-in weightings — best under "Agentic", worst under "All sources".
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 →