Released: 2026-02-06
Key:
Score Threshold:
deepseek/deepseek-chat-v3-0324
deepseek
(50 * (4 * 4 + 3)) + (2 * 4)
= 958
anthropic/claude-3.7-sonnet
anthropic
(50 * 4 * 4) + 3
= 803
google/gemini-2.0-flash-001
(50 * (4 + 4 + 3)) - 4 - 2
= 544
x-ai/grok-3-mini-beta
x-ai
(50 * (4 * 4 + 2) + 3)
= 903
mistralai/mistral-medium-3
mistral
((50 + 4) * (4 + 4) * 3) + 2
= 1298
openai/gpt-4o
openai
(50 * 4) + (3 * (4 * 4)) + 2
= 250
qwen/qwen3-235b-a22b
qwen
(50 * (2 + 4) + 4 / 4) * 3
= 903
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.