Released: 2026-09-06
Key:
Score Threshold:
deepseek/deepseek-chat-v3-0324
deepseek
((75 * (50 + 1)) + (100 - 25)) - 2
= 3898
openai/gpt-4o
openai
((75 - 50 + 1) * 25) + 2 + 100
= 752
mistralai/mistral-medium-3
mistral
(100 * (75 - (50 + 2))) + 1
= 2301
moonshotai/kimi-k2.5
moonshot
((75 + 50 * 2) / 25) * 100 - 1
= 699
minimax/minimax-m2.5
minimax
75 * ((100 + 50) / 25 + 2 + 1)
= 675
Each model receives the same prompt with the numbers to use. Models are tasked with creating an expression using only arithmetic operations to reach the target number. Each number can only be used once and you do not have to use all the numbers. Their answers are evaluated without feedback or retries.