Released: 2026-08-10
meta-llama/llama-3.3-70b-instruct
meta
4/4
ANY OLD HOW, AT RANDOM, WILLY-NILLY, HELTER-SKELTER
Phrases meaning without order or planning
MAIL DELIVERY, MOBILE TICKET, PRINT-AT-HOME, WILL CALL
Methods of ticket delivery
BALANCE DUE, BILL TO, ORDER NUMBER, UNIT PRICE
Terms found on an invoice
BILLY GOAT, COLONEL SANDERS, DOCTOR STRANGE, THE DEVIL
Names of famous goats, or individuals with distinctive titles
openai/gpt-4o
openai
4/4
ANY OLD HOW, AT RANDOM, HELTER-SKELTER, WILLY-NILLY
Synonyms for ’randomly’
MAIL DELIVERY, MOBILE TICKET, PRINT-AT-HOME, WILL CALL
Types of ticket delivery methods
BALANCE DUE, BILL TO, ORDER NUMBER, UNIT PRICE
Invoice components
BILLY GOAT, COLONEL SANDERS, DOCTOR STRANGE, THE DEVIL
Character names
mistralai/mistral-medium-3
mistral
4/4
ANY OLD HOW, AT RANDOM, HELTER-SKELTER, WILLY-NILLY
Phrases meaning ’in a disorderly manner’
MAIL DELIVERY, MOBILE TICKET, PRINT-AT-HOME, WILL CALL
Types of ticket delivery methods
BALANCE DUE, BILL TO, ORDER NUMBER, UNIT PRICE
Terms found on an invoice
BILLY GOAT, COLONEL SANDERS, DOCTOR STRANGE, THE DEVIL
Names associated with goats, chicken, magic, and evil respectively
deepseek/deepseek-chat-v3-0324
deepseek
4/4
ANY OLD HOW, AT RANDOM, HELTER-SKELTER, WILLY-NILLY
Synonyms for haphazard or random
MAIL DELIVERY, MOBILE TICKET, PRINT-AT-HOME, WILL CALL
Ways to receive tickets or deliveries
BALANCE DUE, BILL TO, ORDER NUMBER, UNIT PRICE
Common invoice terms
BILLY GOAT, COLONEL SANDERS, DOCTOR STRANGE, THE DEVIL
Names with titles
Each model receives the same prompt with the 16 words to connect. Models are tasked with creating 4 connections and their answers are evaluated without feedback or retries.