Stay connected with us on X, Discord, and LinkedIn to stay up to date with future analysis
For EnterpriseInsights
All MicroEvals
Arithmetic
Create MicroEval
Header image for Arithmetic

Arithmetic

What complexity of arithmetic is it safe to trust LLMs to do without a code interpreter? The purpose of this eval is to understand what level is completely safe, and what level you should instruct and LLM to use a

Prompt

What is the answer to 34,567.89 + 12,345.67?

Answer guidance

46,913.56

Google logoGoogleGemma 3 4B Instruct
Drag to resize
Google logoGoogleGemini 2.5 Pro
Drag to resize
OpenAI logoOpenAIgpt-oss-20B (high)
Drag to resize
OpenAI logoOpenAIGPT-4.1
Drag to resize
Alibaba logoAlibabaQwen3 235B A22B (Non-reasoning)

Response not available

Drag to resize
xAI logoxAIGrok 4
Drag to resize
OpenAI logoOpenAIGPT-4.1 nano
Drag to resize
DeepSeek logoDeepSeekDeepSeek V3 0324
Drag to resize
Meta logoMetaLlama 4 Maverick
Drag to resize
DeepSeek logoDeepSeekDeepSeek R1 0528 (May '25)
Drag to resize
Meta logoMetaLlama 4 Scout
Drag to resize
Alibaba logoAlibabaQwen3 8B (Non-reasoning)
Drag to resize
OpenAI logoOpenAIGPT-5 nano (high)
Drag to resize
OpenAI logoOpenAIgpt-oss-120B (high)
Drag to resize