Released: 2026-04-18
Key:
Score Threshold:
deepseek/deepseek-chat-v3-0324
deepseek
(100 + 50) * 4 + 75 + 25 - 6
= 694
x-ai/grok-3-mini-beta
x-ai
((75 * (6 + (50 / 25))) + 100) - 4
= 696
openai/gpt-4o
openai
((75 * 4) + 100) - (50 / 25)
= 398
anthropic/claude-3.7-sonnet
anthropic
(75 + 25) * 6 + 100 + 4 + 50
= 754
z-ai/glm-5
z-ai
(100 * 6) + 75 + (50 / 25) * 4
= 683
minimax/minimax-m2.5
minimax
75*6+100+50+25+4
= 629
mistralai/mistral-medium-3
mistral
(100 * 75) - (25 * 6) - (50 / 4)
= 7337
moonshotai/kimi-k2.5
moonshot
(100 - 75) * 25 + 50 + 4 + 6
= 685
google/gemini-2.0-flash-001
(6 * (100 + 75)) - (50 + 25 + 4)
= 971
google/gemini-3-flash-preview
((100 + 4) * 6) + 50 + 75 / 25
= 677
anthropic/claude-sonnet-4.6
anthropic
6 * 100 + 75 + 4 * 25 - 50
= 725
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.