https://github.com/brianpeiris/llm-basic-letter-counting-benchmark

A basic letter-counting benchmark for LLMs
https://github.com/brianpeiris/llm-basic-letter-counting-benchmark

ai gpt llm

Last synced: 4 months ago
JSON representation

A basic letter-counting benchmark for LLMs

• Host: GitHub
• URL: https://github.com/brianpeiris/llm-basic-letter-counting-benchmark
• Owner: brianpeiris
• License: mit
• Created: 2024-07-29T00:47:52.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-07-29T01:49:51.000Z (almost 2 years ago)
• Last Synced: 2026-01-18T22:34:05.428Z (5 months ago)
• Topics: ai, gpt, llm
• Language: TypeScript
• Homepage: https://brianpeiris.github.io/llm-basic-reasoning-benchmark/
• Size: 19.5 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# A Basic Letter-Counting Benchmark for LLMS

Code for a letter-counting benchmark for LLMs; Measuring how reliably LLMs can

answer prompts like "How many times does the letter 'r' appear in the word 'barrier'?".

More information in the blog post: https://brianpeiris.github.io/llm-basic-reasoning-benchmark/