B

benchmarks

Analyses reproductibles et nettoyées des modèles LLM à partir des données publiques de llm-stats.com (API ZeroEval)

Python research code testing Prophet as a forecasting model. Includes random-walk and autocorrelation simulations, a hyperparameter tuning sweep, M4 hourly, weekly and daily benchmarks against naive, ETS, Theta and MSTL, and a rolling-origin evaluation on the Peyton Manning series.

Benchmark suite comparing global memory allocators (jemalloc, mimalloc) under concurrent load.

Polyglot benchmark suite & interactive performance dashboard comparing 15 programming languages in Alpine Linux

Benchmarks data processing tools

Measured proofs and evidence for GlassBreakr frame generation

Performance benchmarks comparing the Kit programming language with other mainstream languages

Every model. Every agent. Everything AI. Tracked. Benchmark scores, pricing, and rankings for every AI model and provider.

DPS8M Benchmark Visualizer

A port of the open GPU4S benchmark suite to Ada.

Word2vec, FastText, GloVE embedding accuracy comparison using analogy, vector-oriented reasoning, synonym and conjugation datasets from multiple sources.

RMAT Benchmark Files for Bench-marking Parallel Sorting Algorithms