Apps & Tools
Yet Another Applied LLM Benchmark
A practical benchmark for evaluating LLMs on real-world programming tasks
Is this your creation?
Open source
Description
A benchmarking framework that evaluates language models on nearly 100 real-world tasks derived from actual developer queries. It uses a custom dataflow DSL to chain model outputs into execution environments like Docker, allowing for mechanistic verification of code, vision-based verification of renders, and automated grading via an LLM evaluator.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.