Go to example tasks
Compare GPT, Claude and Gemini side by side
Sends the same prompts to GPT-5, Claude Sonnet 5, Gemini 3.8 Flash and Perplexity Sonar, then returns one row per model per prompt with the answer, the cost and the token count. Use it to pick a model on evidence from your own prompts instead of a benchmark table, before you commit to one in production.
Bulk LLM Runner GPT, Claude, Perplexity, Kimi (No API Key)fayoussef/bulk-llm-runner
Prompt
Model
Response
Tools used
+3 fieldsTextNumberBooleanListObject
Input
Prompts(required):Explain what a vector database is to a non technical product manager, in under 120 words.+2
Compare with extra models:openai/gpt-5+3
System prompt (optional):You are a helpful, accurate assistant. Answer directly and concisely.
Response format:text
Output fields
Prompt
Model
Response
Tools used
Cost (USD)
Tokens
Error
Sign up on Apify01
Create your Apify account to access the Bulk LLM Runner GPT, Claude, Perplexity, Kimi (No API Key).
Start the run02
The Actor will start running based on the input automatically.
Receive the output03
Monitor the progress in real-time. You will be notified as soon as your dataset is complete and ready for review.
Integrate into your workflow04
The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow.
