Released: 2026-07-11
Key:
Score Threshold:
openai/gpt-4o
openai
(3 + 9) * 25 - 7
= 293
google/gemini-3-flash-preview
(3 * 100) - 25 - 7
= 268
deepseek/deepseek-chat-v3-0324
deepseek
(100 - (9 - 7)) * 3 + 50
= 344
anthropic/claude-sonnet-4.6
anthropic
50 * (3 + 7) - 100 / (25 - 9)
= 493
minimax/minimax-m2.5
minimax
100 * 3 - 50 + 25 - 7
= 268
moonshotai/kimi-k2.5
moonshot
25 * 9 + 50 - 7
= 268
mistralai/mistral-medium-3
mistral
((100 + 50) * (9 - 3)) + (25 + 7)
= 932
z-ai/glm-5
z-ai
25 * 9 + 50 - 7
= 268
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.