INTELLECT 1 Instruct — Benchmarks

Benchmark scores for INTELLECT 1 Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #45 of 73 open modelscomposite 40.3/100 across 4 benchmarks in 3 categories · methodology

Knowledge

Benchmark	Score	Open rank	All models
HellaSwag	71.4%	#27 / 42	#49 / 76
MMLU	49.9%	#59 / 76	#109 / 136

Math

Benchmark	Score	Open rank	All models
GSM8K	38.6%	#35 / 59	#52 / 93

Reasoning

Benchmark	Score	Open rank	All models
BIG-Bench Hard	34.8%	#32 / 37	#45 / 50

Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.