Released: 2026-02-27
Key:
Score Threshold:
google/gemini-2.0-flash-001
((100 * 9) - 3) - (10 + 2 + 5)
= 880
mistralai/mistral-medium-3
mistral
((100 + 3) * (10 - (9 / (5 + 2))))
= 897
google/gemini-3-flash-preview
(100-3+10)*9-5+2
= 960
anthropic/claude-3.7-sonnet
anthropic
(100 - 10) * 9 + 5 + 2
= 817
minimax/minimax-m2.5
minimax
((100 + 10) * 9) - (5 * 2) + 3
= 983
anthropic/claude-sonnet-4.6
anthropic
9 * 100 - 10 - 5 - 3 * 2
= 879
deepseek/deepseek-chat-v3-0324
deepseek
((100 * 9) - (10 * 2)) + 5 + 3
= 888
x-ai/grok-3-mini-beta
x-ai
(100 - (2 * 5 + 3)) * 10 + 9
= 879
moonshotai/kimi-k2.5
moonshot
100 * 9 - 3 * (10 - 5 + 2)
= 879
openai/gpt-4o
openai
(100 * 9) - 3 + 2
= 899
z-ai/glm-5
z-ai
100 * 9 - (10 - 3) * (5 - 2)
= 879
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.