granite-4.0-1b

granite-4.0-1b.

Released 28 Oct 2025

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Unknown lab Oct 2025

No Epoch Capabilities Index score yet

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Benchmark	Score	Rank	Source
AGIEval	49.2%	#22 of 35	Model card
BIG-Bench Hard	60.4%	#57 of 71	Model card
IFEval	77.4%	#106 of 126	Model card
MMLU	59.4%	#114 of 127	Model card
MGSM	37.8%	#50 of 52	Model card
MMLU-Pro	34%	#148 of 151	Model card
MMMLU	45%	#61 of 62	Model card
INCLUDE	42.1%	#25 of 25	Model card

Benchmark	Score	Rank	Source
GSM8K	76.3%	#65 of 87	Model card
MATH	45.3%	#70 of 93	Model card
GPQA Diamond	24%	#212 of 219	Epoch AI
OTIS Mock AIME 2024-2025	0.83%	#196 of 202	Epoch AI
DeepMind Mathematics	34%	#4 of 4	Model card
GSM-Symbolic	72.3%	#3 of 3	Model card

Benchmark	Score	Rank	Source
HumanEval	74%	#60 of 95	Model card
MBPP	65%	#46 of 66	Model card
HumanEval+	69%	#24 of 27	Model card
MultiPL-E	32.2%	#18 of 18	Model card
MBPP+	57%	#15 of 15	Model card
BigCodeBench	30.2%	#11 of 11	Model card
CRUXEval	33.1%	#9 of 9	Model card

Benchmark	Score		Rank	Source
Berkeley Function Calling Leaderboard (BFCL)	54.8%		#45 of 47	Model card

Benchmark	Score		Rank	Source
AttaQ	85.3%		#5 of 5	Model card
SALAD-Bench	93.4%		#3 of 3	Model card

The benchmarks the lab chose to headline, with the scores it gave.