Released: 2026-02-09
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
(75 * (8 + 4)) - (50 + 25 + 1)
= 824
openai/gpt-4o
openai
(75 * 4) - (50 / 25) + 8 - 1
= 305
deepseek/deepseek-chat-v3-0324
deepseek
(75 - 25) * 4 + 8 - 1
= 207
google/gemini-2.0-flash-001
(75 * 4) - (50 + 25 - 8 - 1)
= 234
x-ai/grok-3-mini-beta
x-ai
(25 * 8) + 4
= 204
qwen/qwen3-235b-a22b
qwen
4*(50 + 1)
= 204
anthropic/claude-3.7-sonnet
anthropic
(75 - 50) * (4 + 1) * 8
= 1000
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.