Released: 2026-02-05
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 * 6) + 50 - 5
= 495
mistralai/mistral-medium-3
mistral
((75 + 50 - 6) * (3 + 25)) - 5
= 3327
anthropic/claude-3.7-sonnet
anthropic
((75 + 6) * (3 + 5)) + 25
= 673
openai/gpt-4o
openai
(75 * 6) + (50 - 25) + 3
= 478
deepseek/deepseek-chat-v3-0324
deepseek
(75 * (6 + (50 / 25))) + 5 + 3
= 608
qwen/qwen3-235b-a22b
qwen
75*(5+6/3)+(50-25)
= 550
x-ai/grok-3-mini-beta
x-ai
((75 * ((50 /5) -3)) + 6)
= 531
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.