Released: 2026-02-10
Key:
Score Threshold:
google/gemini-2.0-flash-001
(100 * 3) + 10 - 6 + 75 - 50
= 329
mistralai/mistral-medium-3
mistral
(100 + 75 + 50 + 10) * (6 - 3)
= 705
openai/gpt-4o
openai
(75 * 3) + 50 - 6 + 10
= 279
deepseek/deepseek-chat-v3-0324
deepseek
(100 * 3) + (75 - (50 - (10 + 6)))
= 341
anthropic/claude-3.7-sonnet
anthropic
(75 - 50) * 10 + 100 + 6 + 3
= 359
x-ai/grok-3-mini-beta
x-ai
((100 + 6) * 3) - 10
= 308
qwen/qwen3-235b-a22b
qwen
((100 + 6) * 3) - 10
= 308
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.