benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
IBM
Granite 4.1 30B
8 benchmarks
GSM8K
#3 of 6
94.16%
HumanEval
#6 of 22
88.41%
HumanEval+
#3 of 5
85.37%
MMLU
#1 of 3
80.16%
MMMLU
#9 of 12
73.71%
BFCL v3
#2 of 5
73.68%
MMLU Pro
#49 of 58
64.09%
GPQA Diamond
#109 of 124
45.76%