Released: 2026-06-16
Key:
Score Threshold:
openai/gpt-4o
openai
100 + 75 + 8 + 6 + 3 - 1
= 191
mistralai/mistral-medium-3
mistral
((100 + 75) * (6 - 1)) - (8 / (3))
= 872
anthropic/claude-sonnet-4.6
anthropic
6 * 100 - 8 - 1
= 591
deepseek/deepseek-chat-v3-0324
deepseek
(100 + 6) * (8 - 3) + 1
= 531
z-ai/glm-5
z-ai
(100 * 6) - (8 + 1)
= 591
minimax/minimax-m2.5
minimax
(100 * 6) - (8 + 1)
= 591
moonshotai/kimi-k2.5
moonshot
(100 * 6) - 8 - 1
= 591
google/gemini-3-flash-preview
(6*100)-8-1
= 591
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.