Released: 2026-03-11
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
(75 * (100 - 6)) - (25 * 3 * 1)
= 6975
deepseek/deepseek-chat-v3-0324
deepseek
((100 + (75 / 25)) * 6) + 1
= 619
anthropic/claude-3.7-sonnet
anthropic
(75 * 100) - ((25 + 1) * (6 - 3))
= 7422
openai/gpt-4o
openai
(75 + 6) * (100 - 1) - 25
= 7994
google/gemini-2.0-flash-001
(100 - 6) * (25 - 1) + 75
= 2331
x-ai/grok-3-mini-beta
x-ai
((100 + 25) * 6 - (3 + 1))
= 746
minimax/minimax-m2.5
minimax
(75-1)*(100/25+6)
= 740
google/gemini-3-flash-preview
(75 * (100 + 25 - 1)) / (3 + 6)
= 1033
moonshotai/kimi-k2.5
moonshot
(75 - 1) * (6 + 100 / 25)
= 740
z-ai/glm-5
z-ai
(100 + 25 - 1) * 6 - 3
= 741
anthropic/claude-sonnet-4.6
anthropic
( 75 + 100) * (25 - 6 * 3) + 1
= 1226
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.