Released: 2026-04-25
Key:
Score Threshold:
deepseek/deepseek-chat-v3-0324
deepseek
100 + 50 + (9 + 2) + 3
= 164
minimax/minimax-m2.5
minimax
100 + 50 + 25 - 9 - 3
= 163
x-ai/grok-3-mini-beta
x-ai
100 + 50 + 25 - 9 - 3
= 163
moonshotai/kimi-k2.5
moonshot
100 + 50 + 25 - 9 - 3
= 163
mistralai/mistral-medium-3
mistral
(100 + 50 + 9) + (25 * (3 + 2))
= 284
google/gemini-2.0-flash-001
(25 * 9) - (100 + 50 + 3 + 2)
= 70
openai/gpt-4o
openai
((100 + 50 + 9) * 2) - 25
= 293
anthropic/claude-3.7-sonnet
anthropic
100 + 50 + 25 - 9 - 3
= 163
z-ai/glm-5
z-ai
100 + 50 + 25 - 9 - 3
= 163
anthropic/claude-sonnet-4.6
anthropic
100 + 50 + 9 + 3 * (25 - 2)
= 228
google/gemini-3-flash-preview
100 + 50 + (25 / (9 / 3)) + 2
= 160
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.