Released: 2026-02-17
Key:
Score Threshold:
openai/gpt-4o
openai
(8 * (100 - (7 - 6)))
= 792
deepseek/deepseek-chat-v3-0324
deepseek
(100 + 6) * (7 - (8 / (50 / 4)))
= 674
anthropic/claude-3.7-sonnet
anthropic
(100 * 7) + (4 * 6)
= 724
mistralai/mistral-medium-3
mistral
((100 + 50) * (8 - (7 - 6))) + 4
= 1054
google/gemini-2.0-flash-001
(100 * 7) + 6 - (8 - 4) + 50
= 752
minimax/minimax-m2.5
minimax
100 * 7 + 4
= 704
z-ai/glm-5
z-ai
(100 * 7) + 4
= 704
x-ai/grok-3-mini-beta
x-ai
(100 * 7) + 4
= 704
moonshotai/kimi-k2.5
moonshot
7 * 100 + 4
= 704
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.