Released: 2026-02-18
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 * (5 + 4)) + 7 - 5
= 677
openai/gpt-4o
openai
((75 * 7) - 4) + (5 * 5)
= 546
mistralai/mistral-medium-3
mistral
((75 + 5) * (7 + 4 + 5)) - 4
= 1276
anthropic/claude-3.7-sonnet
anthropic
75 * (4 + 5) - 7 - 4 - 5
= 659
deepseek/deepseek-chat-v3-0324
deepseek
((75 + 5) * (7 + 4)) - 4
= 876
x-ai/grok-3-mini-beta
x-ai
((75 + 7) * (4 + 4))
= 656
z-ai/glm-5
z-ai
(75 + 7) * (4 + 4)
= 656
minimax/minimax-m2.5
minimax
(75 * 4 * 5) - (7 * 4 * 5)
= 1360
moonshotai/kimi-k2.5
moonshot
(75+5*4)*7-4-5
= 656
google/gemini-3-flash-preview
(75 + 7) * (4 + 4)
= 656
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.