close

DEV Community

# benchmarking

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
How I Built a 95K-Line Cognitive AI Pipeline That Takes an 8B Model to GPT-4 Territory
subhansh profile
near

How I Built a 95K-Line Cognitive AI Pipeline That Takes an 8B Model to GPT-4 Territory

#ai #machinelearning #python #benchmarking
Comments
4 min read
Your model speed benchmark is measuring the wrong thing
thousand_miles_ai profile

Your model speed benchmark is measuring the wrong thing

#discuss #ai #llm #benchmarking
Comments
3 min read
LLM Benchmark Rankings 2026: 15 Models Tested on 38 Real Coding Tasks
ianlpaterson profile

LLM Benchmark Rankings 2026: 15 Models Tested on 38 Real Coding Tasks

#ai #llm #programming #benchmarking
Comments
28 min read
Google Said It Had Native Function Calling. I Tested It.
vystartasv profile

Google Said It Had Native Function Calling. I Tested It.

#ai #agents #localai #benchmarking
Comments
3 min read
We Tested 10 Untested LLMs on Agent Coding — The Results Are In
vystartasv profile

We Tested 10 Untested LLMs on Agent Coding — The Results Are In

#ai #llm #programming #benchmarking
BERJAYA 3
Comments
3 min read
We Benchmarked SupportSage Against Traditional Supports: Here's the Data
lanternproton profile

We Benchmarked SupportSage Against Traditional Supports: Here's the Data

#3dprinting #python #datascience #benchmarking
Comments
3 min read
Why I spun my benchmark into its own repo (and why every dev tool with a benchmark should)
nike-17 profile

Why I spun my benchmark into its own repo (and why every dev tool with a benchmark should)

#opensource #benchmarking #devtools #ai
Comments
4 min read
KVQuant / BitForge: same model, smarter context, better answer
aman_sachan_126d19c4a2773 profile

KVQuant / BitForge: same model, smarter context, better answer

#ai #benchmarking #python #opensource
Comments
1 min read
Qwen sky proof: compressed memory made a tiny model behave better — with the receipts
aman_sachan_126d19c4a2773 profile

Qwen sky proof: compressed memory made a tiny model behave better — with the receipts

#ai #llm #python #benchmarking
Comments
1 min read
Why You Should Never Use std::unordered_set in Hot C++ Loops
dubeykartikay profile

Why You Should Never Use std::unordered_set in Hot C++ Loops

#cpp #performance #algorithms #benchmarking
BERJAYA 1
Comments
2 min read
Gemini-3-Flash: My ai agent benchmark terminalbench Win & 3 Fixes
umair24171 profile

Gemini-3-Flash: My ai agent benchmark terminalbench Win & 3 Fixes

#aiagents #benchmarking #gemini3flash #terminalbench
BERJAYA 1
Comments
7 min read
The Last Pivot: Why Quality Gates Killed My Final KV-Cache Speedup
alankritverma profile

The Last Pivot: Why Quality Gates Killed My Final KV-Cache Speedup

#machinelearning #ai #research #benchmarking
Comments
7 min read
184 MCP installs and a 93.9% adversarial signal GPT-4o can't replicate
agentoracle profile

184 MCP installs and a 93.9% adversarial signal GPT-4o can't replicate

#ai #benchmarking #python #agents
Comments
4 min read
A 70ms Local NLI Judge Hits 0.596 Pearson r With Groq Llama 3.3 70B on DSPy Reward Scoring
akhona_eland_072dac9e0c2c profile

A 70ms Local NLI Judge Hits 0.596 Pearson r With Groq Llama 3.3 70B on DSPy Reward Scoring

#dspy #llm #python #benchmarking
Comments
5 min read
How to Benchmark LLM Inference Performance: TTFT, ITL, and Throughput Metrics
wheynelau profile

How to Benchmark LLM Inference Performance: TTFT, ITL, and Throughput Metrics

#llm #benchmarking #rust #performance
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.