DEV Community

#benchmarking

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
IdeaGene-Bench: A New Benchmark for Scientific Lineage Reasoning in AI

IdeaGene-Bench: A New Benchmark for Scientific Lineage Reasoning in AI

Comments
4 min read
I benchmarked my document-extraction API against Textract and Google DocAI — on public datasets, in public CI

I benchmarked my document-extraction API against Textract and Google DocAI — on public datasets, in public CI

Comments 1
3 min read
How I Benchmarked an LLM Running Entirely on a Phone (No Cloud, No API)

How I Benchmarked an LLM Running Entirely on a Phone (No Cloud, No API)

Comments
16 min read
Is AI-Generated Code Buggier? The 2025-26 Data

Is AI-Generated Code Buggier? The 2025-26 Data

Comments 1
3 min read
Four Performance Bugs AI Coders Introduce Every Day

Four Performance Bugs AI Coders Introduce Every Day

Comments
4 min read
prima.cpp local llm benchmark: 15% Faster Than llama.cpp

prima.cpp local llm benchmark: 15% Faster Than llama.cpp

Comments
8 min read
My Code, My Test, and My Prompt All Agreed. All Three Were Wrong.

My Code, My Test, and My Prompt All Agreed. All Three Were Wrong.

Comments
10 min read
Building an Official Performance Baseline for Vix.cpp Core v2.6.3

Building an Official Performance Baseline for Vix.cpp Core v2.6.3

Comments
3 min read
I measure how fast 42 LLMs actually answer. Here's the honest method.

I measure how fast 42 LLMs actually answer. Here's the honest method.

1
Comments 1
2 min read
Comparing Node.js Postgres Client Libraries: brianc/node-postgres vs. porsager/postgres for Efficiency and Use Cases

Comparing Node.js Postgres Client Libraries: brianc/node-postgres vs. porsager/postgres for Efficiency and Use Cases

1
Comments
10 min read
My AI memory benchmark said 98.3%. The number was true — and worthless.

My AI memory benchmark said 98.3%. The number was true — and worthless.

Comments 13
4 min read
The Mean Is Lying to You: Benchmarks Hide the Variance That Breaks Prod

The Mean Is Lying to You: Benchmarks Hide the Variance That Breaks Prod

1
Comments
5 min read
I needed up-to-date .NET mapper benchmarks. They didn't exist. So I built them.

I needed up-to-date .NET mapper benchmarks. They didn't exist. So I built them.

1
Comments
3 min read
How do you benchmark a product you built yourself?

How do you benchmark a product you built yourself?

1
Comments
2 min read
Benchmarking API reliability under load: when zero downtime migration becomes critical

Benchmarking API reliability under load: when zero downtime migration becomes critical

Comments
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.