Released: 2026-07-01
Key:
Score Threshold:
openai/gpt-4o
openai
(3 + 9) * 8 + 75 + 3
= 174
mistralai/mistral-medium-3
mistral
(100 + 75) + (9 * (8 + 3) + 3)
= 277
deepseek/deepseek-chat-v3-0324
deepseek
(100 * 3) - (75 - (9 + 8))
= 242
anthropic/claude-sonnet-4.6
anthropic
((100 + 9) * 3) - 75 + 8 - 3
= 257
minimax/minimax-m2.5
minimax
((100 - (75 - 3)) * 8) - 9 + 3
= 218
moonshotai/kimi-k2.5
moonshot
(100 - 75) * 9 - 8 + 3 / 3
= 218
google/gemini-3-flash-preview
((75 + 3) * 3) - 100 + 8 + 9
= 151
z-ai/glm-5
z-ai
(100 + 9) * (8 - 3 - 3)
= 218
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.