Released: 2026-01-31
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 * (6 + 7)) + (25 - 3) + 3
= 1000
mistralai/mistral-medium-3
mistral
((75 + 25) * (6 * 7)) + (3 / 3)
= 4201
anthropic/claude-3.7-sonnet
anthropic
75 * (3 + 7) + 25 * 3 + 6
= 831
deepseek/deepseek-chat-v3-0324
deepseek
((75 * (7 + 3)) + (25 * 3)) + 6
= 831
x-ai/grok-3-mini-beta
x-ai
7 * (75 + 25 + 6 + 3 + 3)
= 784
openai/gpt-4o
openai
((75 + 7) * (6 + 3)) - 3
= 735
qwen/qwen3-235b-a22b
qwen
((75+6)*(7+3))-(25-3)
= 788
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.