Released: 2026-03-04
Key:
Score Threshold:
deepseek/deepseek-chat-v3-0324
deepseek
(100 + 75) * (9 - 1) - 25 + 10
= 1385
openai/gpt-4o
openai
(25 * 9) + 1 + (100 / 10)
= 236
anthropic/claude-3.7-sonnet
anthropic
75 * 10 / 25 * 100 - 9 - 1
= 2990
minimax/minimax-m2.5
minimax
(100 + 75) + (25 + 10 - 9 + 1)
= 202
x-ai/grok-3-mini-beta
x-ai
(100 + 75 + 25) + (10 - 9 + 1)
= 202
google/gemini-2.0-flash-001
(100 - 75) * (10 - 1) - 25 + 9
= 209
mistralai/mistral-medium-3
mistral
((100 + 75) + (25 * (10 - (9 + 1))))
= 175
moonshotai/kimi-k2.5
moonshot
(75 + 25) + 100 + 10 - 9 + 1
= 202
anthropic/claude-sonnet-4.6
anthropic
100 + 75 + 25 + 1 + 10 - 9
= 202
google/gemini-3-flash-preview
(100 * (25 - 9 - 1)) / 75 + 10
= 30
z-ai/glm-5
z-ai
100 + 75 + 25 + 10 - 9 + 1
= 202
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.