Released: 2026-02-26
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
(75 * (8 + 4)) + (10 * (6 + 4))
= 1000
google/gemini-2.0-flash-001
(75 * 4) - 6 - 4 - 10 + 8
= 288
openai/gpt-4o
openai
(75 * 4) - (6 + 8 + 4)
= 282
google/gemini-3-flash-preview
(4 * (75 - 8)) - (10 - 6)
= 264
deepseek/deepseek-chat-v3-0324
deepseek
(75 * 4) - (10 + 8 + 6 + 4)
= 272
anthropic/claude-3.7-sonnet
anthropic
(75 - 4) * 4 - 6 + 10
= 288
z-ai/glm-5
z-ai
75 + (8 * 6 * 4)
= 267
minimax/minimax-m2.5
minimax
(8*6*4)+75
= 267
moonshotai/kimi-k2.5
moonshot
(75 - 8) * 4 - (10 - 4) / 6
= 267
x-ai/grok-3-mini-beta
x-ai
75 + (8 * 6 * 4)
= 267
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.