#evaluation

El repositorio no publica descripción.

Per-collection OCR leaderboards using VLM-as-judge

Point it at a folder and find out what is missing, and what silently changed. Coverage over dated or numbered series, plus a baseline anyone can keep. No model decides any of it.

Robustness evaluation harness for robot manipulation policies (VLA): perturbation sweeps, failure clustering, reproducible reports.

A highly configurable custom expression tree evaluator

"Unit tests" for your agent skills

Download official Windows ISOs directly from Microsoft's CDN. Web app + CLI tool. No account, no ads, no browser required.

High-fidelity performance metrics for generative models in PyTorch

Skill Eval Tester

This .NET library allows you to evaluate and compile any mathematical expression from a string dynamically at runtime. It supports a wide range of operations and allows for the use of custom variables, operators, and functions. The evaluator can be configured for different contexts, such as scientific, programming, boolean math expressions.

The official Python library for the Epsilab API

A Python library for lazy evaluation with context caching.

Benchmarks, scripts, and runnable ML experiments by Sameer Maurya

While Python SDK (formerly zeroproof): trace ingest, agent simulations, grading, and training data for post-training

Expression evaluation in golang

Your model, many harnesses, many benchmarks.

A Go library and CLI for complete TAOCP solutions, fast and audited solving modes, reproducible model evaluation, and detailed token and list-cost accounting.

official evaluation package of the BraTS segmentation challenges

RAMR — Retrieval-Augmented Memory Reliability: a contamination-resistant synthetic benchmark for agentic-RAG / memory systems (findings + method)

Budget-bounded LLM routing that finds the cheapest model and prompt meeting your accuracy target.