Released: 2026-03-25
Key:
Score Threshold:
anthropic/claude-3.7-sonnet
anthropic
(50 + 6) * (3 * 3 - 1)
= 448
mistralai/mistral-medium-3
mistral
((50 + 3) * (6 + 1)) * 6
= 2226
google/gemini-2.0-flash-001
(3 * (50 + (6 * 6))) - 1
= 257
deepseek/deepseek-chat-v3-0324
deepseek
((50 * (6 + 3)) - 6) - 1
= 443
openai/gpt-4o
openai
(50 * 6) + ((6 / 3) * 3) + 1
= 307
moonshotai/kimi-k2.5
moonshot
50 * (6 + 3 - 1) + 6 + 3
= 409
x-ai/grok-3-mini-beta
x-ai
50 * ((6 + 3) - 1) + (6 + 3)
= 409
minimax/minimax-m2.5
minimax
50*6+6*3+3+1
= 322
z-ai/glm-5
z-ai
50 * (6 + 3 - 1) + 6 + 3
= 409
anthropic/claude-sonnet-4.6
anthropic
50 * (6 + 3) - 6 * (3 - 1)
= 438
google/gemini-3-flash-preview
((50 + 6 + 1) * 6) + (3 * 3)
= 351
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.