Released: 2026-08-22
Key:
Score Threshold:
openai/gpt-4o
openai
(75 * 7) - ((10 - 4) * 25)
= 375
mistralai/mistral-medium-3
mistral
((75 + 25) * (10 + 4)) - (7 * 6)
= 1358
deepseek/deepseek-chat-v3-0324
deepseek
((75 * (10 - 4)) + (25 - 7))
= 468
z-ai/glm-5
z-ai
(75 * 7) - ((25 + 4) - 6)
= 502
minimax/minimax-m2.5
minimax
75*7-25+6-4
= 502
moonshotai/kimi-k2.5
moonshot
((75 + 25) * 6) - 10 + (7 * 4)
= 618
google/gemini-3-flash-preview
(75 * 6) + (10 * 7) - (25 - 4)
= 499
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.