Released: 2026-05-18
Key:
Score Threshold:
google/gemini-2.0-flash-001
(100 * 4) - 75 + 1 - 10
= 316
google/gemini-3-flash-preview
(4 * (75 - 10)) + (100 / 25)
= 264
openai/gpt-4o
openai
((100 + 10) * 4) - (75 - 25)
= 390
deepseek/deepseek-chat-v3-0324
deepseek
(100 - (75 / 25)) * (10 - 1)
= 873
z-ai/glm-5
z-ai
4 * (75 - 10 + 1)
= 264
minimax/minimax-m2.5
minimax
(75 * 4) - 25 - 10 - 1
= 264
moonshotai/kimi-k2.5
moonshot
(75 - 25) * 4 + 100 - 10 + 1
= 291
mistralai/mistral-medium-3
mistral
(100 + 75) + (25 * (10 - (4 / 1)))
= 325
anthropic/claude-sonnet-4.6
anthropic
((75 - 10) * 4) + 25 - 1
= 284
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.