Released: 2026-04-24
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
(100 - (25 - (9 + 2))) * (8 + 1)
= 774
openai/gpt-4o
openai
(100 * 9) - (25 + 8 + 2) + 1
= 866
google/gemini-2.0-flash-001
(100 * 8) - (25 - 9 + 1) * 2
= 766
deepseek/deepseek-chat-v3-0324
deepseek
((100 + 9) * (8 - 2)) - 25 - 1
= 628
x-ai/grok-3-mini-beta
x-ai
((100 * (8 - 2)) - (9 + 1))
= 590
moonshotai/kimi-k2.5
moonshot
100 * (8 - 2) - (9 + 1)
= 590
anthropic/claude-3.7-sonnet
anthropic
(100 * 9) - 8 - 2
= 890
minimax/minimax-m2.5
minimax
100 * (8 - 2) - 9 - 1
= 590
z-ai/glm-5
z-ai
((8 - 2) * 100) - (9 + 1)
= 590
google/gemini-3-flash-preview
(100 - 25) * 8 - (1 + 9)
= 590
anthropic/claude-sonnet-4.6
anthropic
100 * (8 - 2) - 9 - 1
= 590
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.