Released: 2026-03-29
Key:
Score Threshold:
google/gemini-2.0-flash-001
(25 * 8) - (4 * 2) - 3 - 1
= 188
google/gemini-3-flash-preview
(25 + 1) * (8 - 2) - 3
= 153
openai/gpt-4o
openai
(25 * 4 * 2) - 1
= 199
anthropic/claude-3.7-sonnet
anthropic
(25 * 2 * 3) + (4 + 1)
= 155
mistralai/mistral-medium-3
mistral
((25 * (8 - 1)) * 3) + (4 * 2)
= 533
deepseek/deepseek-chat-v3-0324
deepseek
(25 * (8 - 2)) + 3
= 153
x-ai/grok-3-mini-beta
x-ai
25 * (2 * 3) + (4 - 1)
= 153
minimax/minimax-m2.5
minimax
25 * (8 - 2) + 3 * 1
= 153
z-ai/glm-5
z-ai
25 * (4 + 2) + 3
= 153
moonshotai/kimi-k2.5
moonshot
25 * (4 + 2) + 3
= 153
anthropic/claude-sonnet-4.6
anthropic
((25 - 2) * 8) - (4 - 3 + 1)
= 182
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.