GPT J 6B — Benchmarks

Benchmark scores for GPT J 6B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Knowledge

BenchmarkScoreOpen rankAll models
HellaSwag66.2%#34 / 42#61 / 76
ARC Challenge36.3%#43 / 51#67 / 77
BoolQ65.4%#27 / 33#62 / 77
OpenBookQA38.2%#17 / 21#35 / 42
MMLU25.7%#77 / 77#135 / 136

Reasoning

BenchmarkScoreOpen rankAll models
WinoGrande64.5%#34 / 46#64 / 80
PIQA75.4%#30 / 35#53 / 60

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

GPT J 6B Benchmarks — Scores & Rankings | llmrun