Released: 2026-02-15
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 * 7) + (10 - 1) - 7
= 527
mistralai/mistral-medium-3
mistral
((75 * 7) * (7 + 1)) + (10 * 7)
= 4270
openai/gpt-4o
openai
(75 * 7) + (7 * 10) + 1
= 596
deepseek/deepseek-chat-v3-0324
deepseek
(75 - (7 / 7)) * (10 - 1)
= 666
x-ai/grok-3-mini-beta
x-ai
((75 + (10 - 7 + 1)) * 7)
= 553
z-ai/glm-5
z-ai
7 * (75 + 7 + 7 - 10)
= 553
moonshotai/kimi-k2.5
moonshot
(75 + 10) * 7 - (7 - 1) * 7
= 553
anthropic/claude-3.7-sonnet
anthropic
75 * 7 + 7 * 7 - 1
= 573
qwen/qwen3-235b-a22b
qwen
(75 * 7) + (7 * (10 + 1 - 7))
= 553
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.