Released: 2026-07-04
Key:
Score Threshold:
openai/gpt-4o
openai
(75 - 10) * (9 - 3) + 9
= 399
mistralai/mistral-medium-3
mistral
(75 * (9 - 3)) + (50 + 10 + 9)
= 519
google/gemini-3-flash-preview
(3 * (75 + 50)) - (9 + 9)
= 357
anthropic/claude-sonnet-4.6
anthropic
50 * (9 - 3) + 9 - 75 + 10
= 244
deepseek/deepseek-chat-v3-0324
deepseek
(75 - (9 / 9)) * (10 - 3)
= 518
moonshotai/kimi-k2.5
moonshot
10 * (50 - 9) - 75 - 9 * 3
= 308
minimax/minimax-m2.5
minimax
(75 + 10) * 3 + 50 + 9 - 9
= 305
z-ai/glm-5
z-ai
(9 * 9 * 3) + 75 - 10
= 308
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.