BenchLeader

Granite 4.0 Nano 1B

Quality#323 of 339
34.8Index
Bottom quarter
−15.1 on the median

As of 15 Nov 2026, Granite 4.0 Nano 1B by IBM scores 34.8 on the BenchLeader Index (611 ranked configurations), with its best results in agents & tools (34) and weakest in reasoning (20). Released 28 Oct 2025.

Key facts (as of 15 Nov 2026)

  • Granite 4.0 Nano 1B was released on 28 Oct 2025 (IBM).

In detail. Granite 4.0 Nano 1B is an IBM open-weights model, released 28 Oct 2025. Its best configuration ranks #596 of 611 on the BenchLeader Index at 34.8 ±3.9, in the lower half. The ± is the point: 79 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in agents & tools (34) and lowest in reasoning (20). Last measured 28 Oct 2025.stale: no new result in six months

Blended price
–
Output speed
–
First answer
–
Context
128k
via Artificial Analysis
Cost per task
–
Tokens per task
–
Released
28 Oct 2025
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index35
  2. Reasoning20
  3. Agents & tools34
  4. Maths23
  5. Instruction following26
  6. Long context26

Embed this rank

More badge styles
[![Granite 4.0 Nano 1B on BenchLeader: #318 overall](https://www.benchleader.com/badge/granite-4-0-nano-1b.svg?style=compact)](https://www.benchleader.com/models/granite-4-0-nano-1b)

Paste it at the top of README.md, beside your other badges. The badge redraws with every data update and links back to this page.

Get an email when IBM ships a new model

And once when it gets ranked, plus the weekly review on Mondays.

Choose providers and emails

How its index has moved

20 Oct 2026 to 15 Nov 2026
303439

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Metadata

Benchmarknot statedSource
AA Openness Indexnot in index55.6#39Artificial Analysis

Reasoning

Benchmarknot statedSource
GPQA Diamond24.0%#298Epoch AI Benchmarking Hub
GPQA Diamond (AA)not in index28.1%#541Artificial Analysis
Humanity's Last Exam (AA)not in index4.8%#491Artificial Analysis
CritPtnot in index0.0%#337Artificial Analysis

Coding

Benchmarknot statedSource
LiveCodeBench (AA)not in index4.7%#299Artificial Analysis

Agents & tools

Benchmarknot statedSource
Terminal-Bench Hard0.0%#367Artificial Analysis
τ²-Bench Telecom (AA)not in index22.8%#314Artificial Analysis

Maths

Benchmarknot statedSource
OTIS Mock AIME0.8%#282Epoch AI Benchmarking Hub
AIME 2025 (AA)not in index6.3%#232Artificial Analysis

Instruction following

Benchmarknot statedSource
IFBench20.5%#418Artificial Analysis

Long context

Benchmarknot statedSource
AA-LCR v1.16.0%#508Artificial Analysis

Composite

Benchmarknot statedSource
AA Intelligence Index v4.3.2not in index5.0#621Artificial Analysis
AA Progress Index v1not in index114.2#618Artificial Analysis

More from IBM

New this month

See also

Embed or cite

Show where Granite 4.0 Nano 1B ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page.

[![Granite 4.0 Nano 1B on BenchLeader: #318 overall](https://www.benchleader.com/badge/granite-4-0-nano-1b.svg)](https://www.benchleader.com/models/granite-4-0-nano-1b)

Cite this

The ranking changes daily, so a reference carries the data date. APA style:

BenchLeader. (2026, November 15). Granite 4.0 Nano 1B on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 15, 2026, from https://www.benchleader.com/models/granite-4-0-nano-1b

BibTeX:

@misc{benchleader_granite_4_0_nano_1b_20261115,
  author       = {{BenchLeader}},
  title        = {{Granite 4.0 Nano 1B on the BenchLeader Index (method v1.4)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/granite-4-0-nano-1b}},
  note         = {Data as of 2026-11-15}
}

Every badge style, the embeddable top-10 widget and how to cite the Index

Questions people ask

What are Granite 4.0 Nano 1B's benchmark scores?
As of 15 Nov 2026, Granite 4.0 Nano 1B scores 34.8 ±3.9 on the BenchLeader Index, strongest in agents & tools (34) and weakest in reasoning (20). That rests on independent benchmark results only, and every score on this page links to its publisher.
How does Granite 4.0 Nano 1B rank?
Granite 4.0 Nano 1B is #596 of 611 ranked configurations on 15 Nov 2026. 79 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 72.7.
When was Granite 4.0 Nano 1B released?
IBM released Granite 4.0 Nano 1B on 28 Oct 2025.

Data as of 15 Nov 2026. Compare with another model.

Cite as: BenchLeader, “Granite 4.0 Nano 1B: benchmarks, pricing, speed and rank”, data as of 15 Nov 2026, https://www.benchleader.com/models/granite-4-0-nano-1b.