Released: 2026-05-16
Key:
Score Threshold:
google/gemini-2.0-flash-001
(25 * 9) - (5 + 5 + 6)
= 209
mistralai/mistral-medium-3
mistral
((25 + 6) * (9 - 2)) + (5 * 5)
= 242
openai/gpt-4o
openai
25 * 9 - (6 / 2)
= 222
deepseek/deepseek-chat-v3-0324
deepseek
((25 * 5) + (9 * 6)) + (5 * 2)
= 189
moonshotai/kimi-k2.5
moonshot
(25 * 5) + (9 * 6 * 2) - 5
= 228
z-ai/glm-5
z-ai
(6 + 2) * 25 - 5 / 5
= 199
minimax/minimax-m2.5
minimax
25*9 - 2*5 - 6
= 209
google/gemini-3-flash-preview
(25 * (2 + 6)) - (5 / 5)
= 199
anthropic/claude-sonnet-4.6
anthropic
25 * (5 + 2) + 9 * 6 - 5
= 224
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.