Released: 2026-05-25
Key:
Score Threshold:
google/gemini-3-flash-preview
8 * 100 + 10 + (75 / 25)
= 813
openai/gpt-4o
openai
(100 * 8) + (50 + 75 + 10 - 25)
= 910
deepseek/deepseek-chat-v3-0324
deepseek
((100 + 50 + 10) * (25 - 8)) + 75
= 2795
minimax/minimax-m2.5
minimax
(75 - 8) * 10 + 100
= 770
moonshotai/kimi-k2.5
moonshot
8*100+10+(75-50)/25
= 811
z-ai/glm-5
z-ai
100 * 8 + 10 + (75 - 50) / 25
= 811
google/gemini-2.0-flash-001
((100 * 8) + 25) - 10
= 815
mistralai/mistral-medium-3
mistral
((100 + 75) * (8 - (10 / (25 / 50))))
= -2100
anthropic/claude-sonnet-4.6
anthropic
8 * 100 + 75 - 50 + 10 - 25
= 810
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.