Released: 2026-02-16
Key:
Score Threshold:
google/gemini-2.0-flash-001
((50 * 25) - 6) / 2 + 9
= 631
mistralai/mistral-medium-3
mistral
((50 + 25) * (9 + 6)) + (2 / 2)
= 1126
anthropic/claude-3.7-sonnet
anthropic
50 * (25 - 6) + 9 * 2
= 968
openai/gpt-4o
openai
50 * 9 + 25 + 6 + 2 + 2
= 485
deepseek/deepseek-chat-v3-0324
deepseek
((50 * (25 - 6)) + (9 - 2)) * 2
= 1914
x-ai/grok-3-mini-beta
x-ai
(50 * (25 - 6)) + (9 + 2 + 2)
= 963
z-ai/glm-5
z-ai
50 * (25 - 6) + 9 + 2 + 2
= 963
moonshotai/kimi-k2.5
moonshot
50 * (25 - 6) + 9 + 2 * 2
= 963
qwen/qwen3-235b-a22b
qwen
50*(25 - 6) + 9 + 2 + 2
= 963
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.