Released: 2026-02-21
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 + 25) * (9 + 3) - 50 - 4
= 1146
mistralai/mistral-medium-3
mistral
((75 + 25) * (9 + 3)) + 4
= 1204
deepseek/deepseek-chat-v3-0324
deepseek
((75 * (50 - (25 - 9))) - 4)
= 2546
google/gemini-3-flash-preview
(4 * (25 + 75 + 50 + 9)) - 3
= 633
openai/gpt-4o
openai
((75 + 25) * 4) - (9 * 3)
= 373
anthropic/claude-3.7-sonnet
anthropic
(75 * (50 / 25) - 4) * 9 * 3
= 3942
z-ai/glm-5
z-ai
4 * (75 * 3 + 50 - 25 - 9)
= 964
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.