Released: 2026-06-23
Key:
Score Threshold:
openai/gpt-4o
openai
(50 * (9 + 3)) + 10
= 610
mistralai/mistral-medium-3
mistral
(50 + 6) * (10 + 9) - 25
= 1039
google/gemini-3-flash-preview
(50 + 6) * 10
= 560
deepseek/deepseek-chat-v3-0324
deepseek
(50 * (10 + (9 - 6)))
= 650
z-ai/glm-5
z-ai
(50 + 6) * 10
= 560
moonshotai/kimi-k2.5
moonshot
(50 + 6) * 10
= 560
minimax/minimax-m2.5
minimax
(50 + 6) * 10
= 560
anthropic/claude-sonnet-4.6
anthropic
((50 + 9 + 3) * 10) - 25 - 6
= 589
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.