Benchmark

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Venkata Manideep Patibandla

Apr 18

I Prompted 5 Frontier LLMs to “Report Uncertainty” Here’s What Happened to Their Statistical Validity Scores

#ai #llm #benchmark #rag

2 min read

James AI

Apr 17

Opus 4.7 First Look: I Tested the Day-Old Model Against 3 Other Claudes on 10 Real Tasks

#ai #llm #claude #benchmark

5 min read

SEN LLC

Apr 16

Writing an HTTP Load Tester That Doesn't Lie About p99

#rust #benchmark #http #tutorial

8 min read

Aakash Gour

Apr 16

I Tested OpenAI, Anthropic, and Cohere for Bulk Content Generation. Here's What the Data Actually Shows.

#ai #openai #api #benchmark

7 min read

SEN LLC

Apr 15

Micro-benchmarking TypeScript Without Lying to Yourself

#typescript #benchmark #cli #tutorial

8 min read

Agent Paaru

Apr 10

I Benchmarked 8 Ollama Cloud AI Models. The 397B One Lost to a 1.6s Model.

#ai #ollama #benchmark #cloud

3 min read

NY-squared2-agents

Apr 8

I benchmarked GPT-4o, Claude 3.5, and Gemini 1.5 for security — the results

#ai #security #llm #benchmark

2 min read

João André Gomes Marques

Apr 7

NexusQuant vs KVTC vs TurboQuant vs CommVQ — honest comparison

#machinelearning #llm #performance #benchmark

4 min read

DevOnBike

Apr 5

🚀 8x Faster Than ONNX Runtime: Zero-Allocation AI Inference in Pure C#

#dotnet #performance #ai #benchmark

3 min read

Max Quimby

Mar 29

ARC-AGI V3 Explained: The New AI Benchmark That Breaks Every Agent

#ai #machinelearning #agents #benchmark

3 min read

ThomasP

Mar 28

GPT-5.1 scored 26%. Gemini 3 Flash scored 74%. Same prompt, same tools.

#ai #llm #benchmark #agents

8 min read

Mitul Shah for Ferro Labs AI

Mar 26

AI Gateways Are Not I/O-Bound Proxies I Benchmarked 5 of Them to Prove It

#ai #go #python #benchmark

9 min read

plasmon

Mar 25

I Tried Speculative Decoding on RTX 4060 8GB — Every Config Was Slower Than Baseline

#llm #gpu #benchmark #ai

8 min read

Tom Lee

Mar 25

FTS vs Hybrid Memory Search: A Real-World Benchmark

#ai #benchmark #search #agents

4 min read

Mininglamp

Apr 14

How Mano-P Achieves #1 on OSWorld: Architecture, Benchmarks, and Edge Deployment

#ai #opensource #agents #benchmark

4 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.

DEV Community

# benchmark

I Prompted 5 Frontier LLMs to “Report Uncertainty” Here’s What Happened to Their Statistical Validity Scores

Opus 4.7 First Look: I Tested the Day-Old Model Against 3 Other Claudes on 10 Real Tasks

Writing an HTTP Load Tester That Doesn't Lie About p99

I Tested OpenAI, Anthropic, and Cohere for Bulk Content Generation. Here's What the Data Actually Shows.

Micro-benchmarking TypeScript Without Lying to Yourself

I Benchmarked 8 Ollama Cloud AI Models. The 397B One Lost to a 1.6s Model.

I benchmarked GPT-4o, Claude 3.5, and Gemini 1.5 for security — the results

NexusQuant vs KVTC vs TurboQuant vs CommVQ — honest comparison

🚀 8x Faster Than ONNX Runtime: Zero-Allocation AI Inference in Pure C#

ARC-AGI V3 Explained: The New AI Benchmark That Breaks Every Agent

GPT-5.1 scored 26%. Gemini 3 Flash scored 74%. Same prompt, same tools.

AI Gateways Are Not I/O-Bound Proxies I Benchmarked 5 of Them to Prove It

I Tried Speculative Decoding on RTX 4060 8GB — Every Config Was Slower Than Baseline

FTS vs Hybrid Memory Search: A Real-World Benchmark

How Mano-P Achieves #1 on OSWorld: Architecture, Benchmarks, and Edge Deployment