LLM Tree Navigation Benchmark
Test LLM tree-nav ability with various prompt engineering mods. Measures the ability of various LLMs to navigate a fictional codebase via iterative directory tree expansion and observation.
Open source
Reactions (1)
Similar products
by description similarity
CodeRLM
github.comTree-sitter-backed code indexing for LLM agents
LLM Explorer
llm.extractum.ioFind your best LLM for a local inference
Promptotype- Develop
promptotype.iotest, and monitor your LLM structured tasks
LLM Prompt & Model Playground
with.context.aiTest LLM prompts & models side-by-side against many inputs
A multi-source LLM benchmark across text, image, and audio that measures JSON value accuracy per field, not just schema compliance. 7 metrics, full leaderboard.