Released: 2026-03-05
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
((75 + 25) * (7 + 3)) - 4
= 996
openai/gpt-4o
openai
(75 * 7) - 25 - (3 + 4)
= 493
google/gemini-2.0-flash-001
(75 * 7) - (25 - 3)
= 503
minimax/minimax-m2.5
minimax
(75 - 3) * (7 + 7 - 4 + 25)
= 2520
deepseek/deepseek-chat-v3-0324
deepseek
(75 - (7 - 4)) * 7 + 25
= 529
anthropic/claude-sonnet-4.6
anthropic
( (7 * 75) - 25) - ( 7 - 3 * 4)
= 505
x-ai/grok-3-mini-beta
x-ai
((75 - 7) * 7) - (4 * 3)
= 464
z-ai/glm-5
z-ai
(75 - 7) * 7 - 4 * 3
= 464
anthropic/claude-3.7-sonnet
anthropic
75 * 7 - (25 + 7 + 4) / 3
= 513
google/gemini-3-flash-preview
(4 * (75 + 25 + 7 + 7 + 3))
= 468
moonshotai/kimi-k2.5
moonshot
7*(75-7)-4*3
= 464
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.