Released: 2026-06-15
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
(100 + 50 + 3) * (8 - (3 / 2))
= 994
deepseek/deepseek-chat-v3-0324
deepseek
(100 + 50) * (8 - (3 + 3))
= 300
anthropic/claude-sonnet-4.6
anthropic
100 * 2 + 50 - 8 * (3 + 3)
= 202
minimax/minimax-m2.5
minimax
(100 - 3) * 2 + (50 - 3 * 8)
= 220
openai/gpt-4o
openai
(50 * 3) + 3 + 2 + (100 - 8)
= 247
moonshotai/kimi-k2.5
moonshot
(100 + 50/(8-3)) * 2
= 220
z-ai/glm-5
z-ai
100 + 50 + 8 * 3 * 3 - 2
= 220
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.