Falcon 180B — Benchmarks

Benchmark scores for Falcon 180B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #16 of 123 open modelscomposite 66.6/100 across 8 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
HellaSwag89.0%#2 / 42#4 / 76
ARC Challenge67.8%#19 / 51#27 / 77
BoolQ89.0%#2 / 33#6 / 77
OpenBookQA64.2%#8 / 21#12 / 42
MMLU70.6%#25 / 77#59 / 136

Math

BenchmarkScoreOpen rankAll models
GSM8K54.4%#28 / 60#41 / 93

Reasoning

BenchmarkScoreOpen rankAll models
WinoGrande87.1%#2 / 46#5 / 80
PIQA84.9%#3 / 35#5 / 60

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