Released: 2026-03-02
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
((75 * (6 + 6)) * (5 + 4)) - 3
= 8097
google/gemini-2.0-flash-001
(75 * 6 * 3) - (6 + 5 + 4)
= 1335
openai/gpt-4o
openai
(75 * (6 + 6 + 5) - 4)
= 1271
anthropic/claude-3.7-sonnet
anthropic
(75 + 4) * (3 + 6 + 5)
= 1106
minimax/minimax-m2.5
minimax
(75 * 6 * 6) - (5 * 4 * 3)
= 2640
deepseek/deepseek-chat-v3-0324
deepseek
((75 + 6) * (6 + 5)) + (4 * 3)
= 903
x-ai/grok-3-mini-beta
x-ai
75 * (4 + 6 + 3) + (6 * 5)
= 1005
z-ai/glm-5
z-ai
(75 + 6 * 6) * (5 + 4)
= 999
anthropic/claude-sonnet-4.6
anthropic
((75 * 6) + (6 * 5 * 4 + 3))
= 573
google/gemini-3-flash-preview
((75*3)+6+6)*4+5
= 953
moonshotai/kimi-k2.5
moonshot
75 * (6 * 3 - 5) + 6 * 4
= 999
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.