Released: 2026-05-10
Key:
Score Threshold:
openai/gpt-4o
openai
(6 * 50) + (9 * (25 + 2))
= 543
google/gemini-2.0-flash-001
((100 + 50) * 2) + 25 + 6 - 9
= 322
anthropic/claude-3.7-sonnet
anthropic
100 * (50 - 25 - 2) - 9 + 6
= 2297
deepseek/deepseek-chat-v3-0324
deepseek
(100 + 50) * (25 - 9) / 6 * 2
= 800
moonshotai/kimi-k2.5
moonshot
9 * 50 + 6
= 456
minimax/minimax-m2.5
minimax
9 * 50 + 6
= 456
z-ai/glm-5
z-ai
(50 * 9) + 6
= 456
x-ai/grok-3-mini-beta
x-ai
50 * 9 + 6
= 456
mistralai/mistral-medium-3
mistral
(100 * (50 - 25)) - (9 * (6 + 2))
= 2428
google/gemini-3-flash-preview
(100 * (50 + 6)) / (25 / 2) + 9
= 457
anthropic/claude-sonnet-4.6
anthropic
100 * (2 + 9) / 25 * (50 - 6)
= 1936
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.