Released: 2026-04-03
Key:
Score Threshold:
google/gemini-2.0-flash-001
((50 * 3) + 25) + 9
= 184
openai/gpt-4o
openai
((25 + 3) * 9) + 3 - 50
= 205
google/gemini-3-flash-preview
(50 + 9) * (3 + 3)
= 354
mistralai/mistral-medium-3
mistral
((50 + 25) * (9 + 3)) * (3 - 1)
= 1800
anthropic/claude-3.7-sonnet
anthropic
(50 * 9) - (25 - 3 - 1)
= 429
deepseek/deepseek-chat-v3-0324
deepseek
(50 * (9 - (1 / 25))) + 3
= 451
z-ai/glm-5
z-ai
(3 + 3) * (50 + 9)
= 354
moonshotai/kimi-k2.5
moonshot
(50 + 9) * (3 + 3)
= 354
x-ai/grok-3-mini-beta
x-ai
50 * (9 - 3 + 1) + 3
= 353
minimax/minimax-m2.5
minimax
(50 + 9) * (3 + 3)
= 354
anthropic/claude-sonnet-4.6
anthropic
50 * (9 - 3) + 25 * (3 - 1)
= 350
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.