Released: 2026-07-08
Key:
Score Threshold:
openai/gpt-4o
openai
100 * 8 - 7 - 3
= 790
mistralai/mistral-medium-3
mistral
((100 + 50) * (8 - 6)) + (7 * 3)
= 321
deepseek/deepseek-chat-v3-0324
deepseek
((100 + 50) * (7 - 3)) + (8 * 6)
= 648
minimax/minimax-m2.5
minimax
(100 + 8) * 7 + 6
= 762
moonshotai/kimi-k2.5
moonshot
(100 + 8) * 7 + 6
= 762
z-ai/glm-5
z-ai
100*3 + ((50+7)*8 + 6)
= 762
anthropic/claude-sonnet-4.6
anthropic
100 * 8 - 50 + 7 + 6 - 3
= 760
google/gemini-3-flash-preview
(100 + 7 + 8 + 3) * 6 + 50
= 758
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.