Released: 2026-04-10
Key:
Score Threshold:
anthropic/claude-3.7-sonnet
anthropic
100 * (2 + 8) - 25
= 975
mistralai/mistral-medium-3
mistral
((100 + 25) * (8 - (7 - (2 / 1))))
= 375
deepseek/deepseek-chat-v3-0324
deepseek
(100 - (25 + 1)) * 7
= 518
minimax/minimax-m2.5
minimax
100 * (7 - 2) - 25
= 475
x-ai/grok-3-mini-beta
x-ai
(100 * (7 - 2)) - 25
= 475
moonshotai/kimi-k2.5
moonshot
100 * (7 - 2) - 25
= 475
google/gemini-2.0-flash-001
(100 * 2) + 25 + 7 + 8 + 1
= 241
openai/gpt-4o
openai
(8 - 1) * (100 - 25) + 7
= 532
google/gemini-3-flash-preview
(100 - 2 - 25) * 7 + 1 - 8
= 504
z-ai/glm-5
z-ai
100 * (7 - 2) - 25
= 475
anthropic/claude-sonnet-4.6
anthropic
100 * (2 + 7) / (1 + 8 - 25)
= -56
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.