Skip to content

Granite-4.0-350M

IBMOpen weightsNon-reasoningProvisionalReleased Oct 28, 2025
Compare with Granite-4.0-H-350MSource scores ↗
Overall score
28.5
Rank 191 of 222 · 14.1–42.8
Context window
32K
32,000 tokens
Price per 1M tokens
— in · — out
No price listed
Blended price
—
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Instruction following#13928.8
  2. 2Reasoning25.0
  3. 3Knowledge18.5
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (7)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Knowledge

GPQA24.1#117 of 117
MMLU-Pro12.1#67 of 67
MMLU35.0#28 of 28

Coding

HumanEval39.0#17 of 18

Reasoning

BBH33.1#7 of 7

Multilingual

MGSM14.7#11 of 11

Instruction following

IFEval55.4#53 of 53

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price———

Self-hosted open-weight model. Public hosted pricing varies by provider.

Open weights

From the Hugging Face repository.

Parameters
352M
Licence
apache-2.0
Downloads (30 days)
24.5K

Speed

Measured by us through OpenRouter (median of trials).

Not available on OpenRouter, so we cannot measure it yet.

Related models

Same family

Similar score