Released: 2026-04-08
Key:
Score Threshold:
google/gemini-2.0-flash-001
((100 * 7) + 50 + 7) - 10
= 747
openai/gpt-4o
openai
(100 * 7) + (10 * 7) + (50 / 2)
= 795
mistralai/mistral-medium-3
mistral
((100 + 50) * 7) - (7 / (10 - 2))
= 1049
anthropic/claude-3.7-sonnet
anthropic
100 * 7 + 50 - 10 - 7 - 2
= 731
x-ai/grok-3-mini-beta
x-ai
(100 * 7) + (10 * 2 + 7)
= 727
z-ai/glm-5
z-ai
7 * 100 + 2 * 10 + 7
= 727
moonshotai/kimi-k2.5
moonshot
(100 + 10) * 7 + 7 - 50
= 727
minimax/minimax-m2.5
minimax
(100 + 50) * 7 - 7 + 10 * 2
= 1063
deepseek/deepseek-chat-v3-0324
deepseek
((100 + 50) * (10 - 7)) + 7
= 457
anthropic/claude-sonnet-4.6
anthropic
100 * 7 + 10 * 2 + 7
= 727
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.