Released: 2026-05-11
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 * 8) + 100 + 50 - 4
= 746
mistralai/mistral-medium-3
mistral
((100 - (25 / (8 - (75 / 50)))) * 4)
= 384
z-ai/glm-5
z-ai
((25 * 4 * 8) + 100) + (50 / 75)
= 900
google/gemini-3-flash-preview
(100 * (50 + 75 + 25) / 8) - 4
= 1871
deepseek/deepseek-chat-v3-0324
deepseek
(100 * (8 + 50 / 25)) + (75 * 4)
= 1300
openai/gpt-4o
openai
((75 * 8) + 100) + 25 + 4
= 729
minimax/minimax-m2.5
minimax
((100 + 75) * 4) + 8 + 50 + 25
= 783
x-ai/grok-3-mini-beta
x-ai
75 * (8 + 4) + (100 / 50)
= 902
moonshotai/kimi-k2.5
moonshot
75 * (8 + 4) + 100 / 50
= 902
anthropic/claude-sonnet-4.6
anthropic
((100 * 8) + (75 * 4)) - 50
= 1050
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.