Released: 2026-05-22
Key:
Score Threshold:
google/gemini-2.0-flash-001
(100 * 7) - 10 - 4 - 2 * 1
= 684
openai/gpt-4o
openai
(100 * 7) - (4 * 2) - 10 - 1
= 681
mistralai/mistral-medium-3
mistral
((100 + 4) * (10 - 2)) * (7 + 1)
= 6656
google/gemini-3-flash-preview
(100 * (7 - 1)) - (10 - 2)
= 592
anthropic/claude-sonnet-4.6
anthropic
(100 + 4) * 7 - 2 * 10 * 1
= 708
deepseek/deepseek-chat-v3-0324
deepseek
(100 * (7 - 1)) - (10 + 4 + 2)
= 584
z-ai/glm-5
z-ai
100 * (7 - 1) - (10 - 2)
= 592
moonshotai/kimi-k2.5
moonshot
(100 - 7) * (4 + 2) + 10
= 568
minimax/minimax-m2.5
minimax
100 * (4 + 2) - (7 + 1)
= 592
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.