Released: 2026-04-27
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 * 9) - (100 - (50 + 4 + 10))
= 639
openai/gpt-4o
openai
(75 + (50 * 10)) + 4
= 579
anthropic/claude-3.7-sonnet
anthropic
(75 * (9 - 4)) + 100 + 50 + 10
= 535
anthropic/claude-sonnet-4.6
anthropic
((75 + 4) * (10 - 9)) * 100 / 50
= 158
deepseek/deepseek-chat-v3-0324
deepseek
(100 + 50) * 4 + 75 + 10 - 9
= 676
moonshotai/kimi-k2.5
moonshot
50 * 10 + 75 + 4
= 579
google/gemini-3-flash-preview
(50 * 10) + 75 + 4
= 579
x-ai/grok-3-mini-beta
x-ai
((75 * 9) - (100 - 4))
= 579
minimax/minimax-m2.5
minimax
100 * (50/10) + 75 + 4
= 579
mistralai/mistral-medium-3
mistral
(100 * (50 - (10 + 9))) - (75 - 4)
= 3029
z-ai/glm-5
z-ai
100 * (50 / 10) + 75 + 4
= 579
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.