Released: 2026-08-02
Key:
Score Threshold:
openai/gpt-4o
openai
(75 * 6) + 50 + 2 - (9 - 5)
= 498
deepseek/deepseek-chat-v3-0324
deepseek
((75 * (9 + 2)) + 50) + 5
= 880
z-ai/glm-5
z-ai
75 * (9 + 5 - 2) + 6
= 906
minimax/minimax-m2.5
minimax
75 * (9 + 5 - 2) + 6
= 906
moonshotai/kimi-k2.5
moonshot
75 * ((50 - 2) / (9 - 5)) + 6
= 906
mistralai/mistral-medium-3
mistral
((75 + 50 + 6) * 9) * 2
= 2358
google/gemini-3-flash-preview
(50 + 75) * (9 - 2) + 6 * 5
= 905
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.