Falcon-180B

Falcon-180B places in the top three on 2 benchmarks.

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Technology Innovation Institute Sep 2023

Open weights

107.1 #207 of 256

Epoch Capabilities Index

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
HellaSwag	89%	#3 of 63	Claim in The Falcon Series of Open Language Models, via Epoch AI
WinoGrande	87.1%	#4 of 76	Claim in The Falcon Series of Open Language Models, via Epoch AI
PIQA	84.9%	#5 of 58	Claim in The Falcon Series of Open Language Models, via Epoch AI
BoolQ	89%	#6 of 61	Claim in The Falcon Series of Open Language Models, via Epoch AI
LAMBADA	79.8%	#3 of 26	Claim in The Falcon Series of Open Language Models, via Epoch AI
MMLU	70.6%	#23 of 85	Claim in The Falcon Series of Open Language Models, via Epoch AI
OpenBookQA	64.2%	#12 of 41	Claim in The Falcon Series of Open Language Models, via Epoch AI
ARC-Challenge	67.8%	#26 of 75	Claim in The Falcon Series of Open Language Models, via Epoch AI
Open Arabic LLM Leaderboard v1	41%	#37 of 55	Official leaderboard
EQ-Bench v2	56.8	#71 of 85	Official leaderboard
LMArena (Elo)	1,148	#309 of 335	Official leaderboard

Benchmark	Score		Rank	Source
GSM8K	54.4%		#33 of 70	Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI

Benchmark	Score		Rank	Source
MultiPL-E	24.1%		#8 of 9	Official leaderboard

Technology Innovation Institute's models in color, against every other model on the Epoch Capabilities Index, by release date.

Source: Epoch Capabilities Index, Epoch AI (CC BY 4.0)