Released: 2026-08-14
Key:
Score Threshold:
openai/gpt-4o
openai
((50 + 25) * 9) - 100 + 3
= 578
google/gemini-3-flash-preview
(3 * 100) + 25 - (50 / (75 / 9))
= 319
deepseek/deepseek-chat-v3-0324
deepseek
50 * (9 - 3) + 100 + 75 - 25
= 450
minimax/minimax-m2.5
minimax
100*3+25-9
= 316
z-ai/glm-5
z-ai
(100 + 25) * 3 - 50 - 9
= 316
mistralai/mistral-medium-3
mistral
((100 + 75) * 3) - (50 / 9)
= 519
moonshotai/kimi-k2.5
moonshot
100 * 3 + 75 - 50 - 9
= 316
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.