Released: 2026-03-26
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 * 2) + 100 + 25 - 50 - 7
= 218
openai/gpt-4o
openai
((50 + 2) * 7) - (100 - 75)
= 339
google/gemini-3-flash-preview
(2 * 100) + 50 + (75 / 25) + 7
= 260
deepseek/deepseek-chat-v3-0324
deepseek
(100 * 2) + 50 + 7 + 75 - 25
= 307
minimax/minimax-m2.5
minimax
100+75+50+25+7+2
= 259
x-ai/grok-3-mini-beta
x-ai
100 + 75 + 50 + 25 + 7 + 2
= 259
moonshotai/kimi-k2.5
moonshot
(75 * 2 + 100 + 50 / 25 + 7)
= 259
mistralai/mistral-medium-3
mistral
(100 + 75 + 50 + 25) + (7 * 2)
= 264
z-ai/glm-5
z-ai
100 + 75 + 50 + 25 + 7 + 2
= 259
anthropic/claude-3.7-sonnet
anthropic
(7 * 50) - 100 + 25 - 2 * 75
= 125
anthropic/claude-sonnet-4.6
anthropic
100 * 2 + 75 - 25 + 7 + 50
= 307
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.