Released: 2026-02-24
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 * 50) / (100 / 2) - 1 - 25
= 49
mistralai/mistral-medium-3
mistral
(100 + 75 + 25 + 50) * (2 + 1)
= 750
deepseek/deepseek-chat-v3-0324
deepseek
(100 + 50 + 1) * 2 + 25
= 327
openai/gpt-4o
openai
(100 + 50 + 75 + 2) - (25 / 1)
= 202
z-ai/glm-5
z-ai
100 + 75 * 2 + 50 + 25 - 1
= 324
google/gemini-3-flash-preview
(50 * (75 - 1)) / (100 / 25) + 2
= 927
x-ai/grok-3-mini-beta
x-ai
((100 * (1 + 2)) + (75 - 50))
= 325
minimax/minimax-m2.5
minimax
75 * (2 + 100/50) + 25 - 1
= 324
anthropic/claude-3.7-sonnet
anthropic
(100 * 2) + (75 * 1) + 50 + 25
= 350
moonshotai/kimi-k2.5
moonshot
(100 - 1) * (75 / 25) + 50 / 2
= 322
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.