Released: 2026-03-31
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
(75 * (10 - (9 / 9))) + (10 * 6)
= 735
google/gemini-2.0-flash-001
(10 * 10) + (9 + 75) - 6 - 9
= 169
deepseek/deepseek-chat-v3-0324
deepseek
(75 * (10 - 6)) + (9 + 9)
= 318
anthropic/claude-3.7-sonnet
anthropic
(9 + 6) * 10 * (10 - 9) + 75
= 225
moonshotai/kimi-k2.5
moonshot
(75 - 10/10) * (9 - 6) - 9
= 213
google/gemini-3-flash-preview
(10 * (75 + 6)) / (10 + 9) + 9
= 51
anthropic/claude-sonnet-4.6
anthropic
75 * (10 - 6) + 9 * (10 - 9)
= 309
minimax/minimax-m2.5
minimax
(10 + 10) * 6 + 75 + 9 + 9
= 213
x-ai/grok-3-mini-beta
x-ai
( (75 * (9 - 6) ) - 10 )
= 215
z-ai/glm-5
z-ai
(10 + 10) * 6 + 75 + 9 + 9
= 213
openai/gpt-4o
openai
(75 + 10 * 9) - 10 + 9
= 164
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.