Released: 2026-02-04
Key:
Score Threshold:
google/gemini-2.0-flash-001
(50 * 9) - (75 - 25) - 8 + 7
= 399
mistralai/mistral-medium-3
mistral
(75 * (8 + (50 / (9 - 7)))) - 25
= 2450
openai/gpt-4o
openai
((75 + 9) * 7) - (50 + 8)
= 530
anthropic/claude-3.7-sonnet
anthropic
75 * (9 - 8) + 50 * 7 + 25
= 450
deepseek/deepseek-chat-v3-0324
deepseek
(75 * (9 - (50 - 25))) + 7 - 8
= -1201
x-ai/grok-3-mini-beta
x-ai
( (50 * 8) + 25 + (9 - 7) )
= 427
qwen/qwen3-235b-a22b
qwen
9*50 - 25 + 8 - 7
= 426
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.