Released: 2026-05-13
Key:
Score Threshold:
google/gemini-3-flash-preview
(8*(75+50))-9*(1+6)
= 937
google/gemini-2.0-flash-001
(75 + 50) * 6 + 1 - 9
= 742
mistralai/mistral-medium-3
mistral
(75 * (9 + (50 - 6))) + (8 / 1)
= 3983
openai/gpt-4o
openai
(50 + 75 + 6) * 8 + 9
= 1057
deepseek/deepseek-chat-v3-0324
deepseek
((75 + 50) * 6) + (9 - 8)
= 751
minimax/minimax-m2.5
minimax
((75 + 50) * 9) + 6 + 8 + 1
= 1140
z-ai/glm-5
z-ai
50 * (8 + 9) - 75 / (6 - 1)
= 835
moonshotai/kimi-k2.5
moonshot
50 * (9 + 8) - 75 / (6 - 1)
= 835
anthropic/claude-sonnet-4.6
anthropic
(75 + 9 - 1) * (50 - 8) / 6
= 581
x-ai/grok-3-mini-beta
x-ai
((75 + 50) * 6 + 9 * 8 + 1)
= 823
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.