close

DEV Community

# benchmark

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Tested CodeGraph on Hono. The Tool-Call Savings Reproduce — the Cost Savings Don't.
harrisonsec profile

I Tested CodeGraph on Hono. The Tool-Call Savings Reproduce — the Cost Savings Don't.

#ai #benchmark #devtools #typescript
Comments
13 min read
We Benchmarked the Most Popular Code Search Tools. We Beat All of Them.
daynablackwell profile

We Benchmarked the Most Popular Code Search Tools. We Beat All of Them.

#ai #mcp #benchmark #devtools
Comments
11 min read
Multi-Shot vs Zero-Shot: When Adding Examples Actually Hurts Accuracy
gabrielanhaia profile

Multi-Shot vs Zero-Shot: When Adding Examples Actually Hurts Accuracy

#ai #llm #prompt #benchmark
Comments
8 min read
Open-Source A3M Router Tops RouterArena Benchmark
megha_mukherjee_5eb776f2b profile

Open-Source A3M Router Tops RouterArena Benchmark

#opensource #llm #benchmark #ai
Comments
1 min read
How does an AI agent pick from 686 skills in a second?
klymentiev profile

How does an AI agent pick from 686 skills in a second?

#ai #benchmark #embeddings #claudecode
Comments
7 min read
LMR-BENCH: Can LLM Agents Reproduce NLP Research Code? (EMNLP 2025)
jangwook_kim_e31e7291ad98 profile

LMR-BENCH: Can LLM Agents Reproduce NLP Research Code? (EMNLP 2025)

#benchmark #researchreproducibility #llmagents #paperpoc
Comments
5 min read
Claude Sonnet 4.6 vs GPT-4.1 vs Gemini 2.5 Flash: which wins JSON extraction?
shaun_vd_7562913ba77e1e0b profile

Claude Sonnet 4.6 vs GPT-4.1 vs Gemini 2.5 Flash: which wins JSON extraction?

#ai #llm #benchmark #claude
Comments
3 min read
Benchmarks- Kubernetes MCP Servers Passed. That Was Not Enough.
vitas profile

Benchmarks- Kubernetes MCP Servers Passed. That Was Not Enough.

#kubernetes #ai #benchmark #opensource
Comments 1
4 min read
We Asked 10 LLMs to Write Efficient Code. Only 4 Got Better.
vystartasv profile

We Asked 10 LLMs to Write Efficient Code. Only 4 Got Better.

#ai #llm #benchmark #programming
Comments
5 min read
10 Models Tested: From 81.6% to 10%. The Free Tier is a Full-On Gamble.
vystartasv profile

10 Models Tested: From 81.6% to 10%. The Free Tier is a Full-On Gamble.

#ai #agents #benchmark #llm
Comments
4 min read
I Tested 10 More Models. Five Brand New Families Debuted. None Scored Below 75%.
vystartasv profile

I Tested 10 More Models. Five Brand New Families Debuted. None Scored Below 75%.

#ai #agents #benchmark #llm
Comments
3 min read
I Benchmarked 15 AI Models for Speed – Here's What Will Blow Your Mind
truelane profile

I Benchmarked 15 AI Models for Speed – Here's What Will Blow Your Mind

#api #ai #performance #benchmark
Image 1
Comments
5 min read
Two Models Just Hit 90% on Agent Coding. One Cost Less Than a Penny.
vystartasv profile

Two Models Just Hit 90% on Agent Coding. One Cost Less Than a Penny.

#ai #agents #benchmark #llm
Comments
2 min read
Model Showdown Round 4: Opus vs Qwen — Writers, Not Coders
carryologist profile
Rob

Model Showdown Round 4: Opus vs Qwen — Writers, Not Coders

#ai #llm #benchmark #agents
Comments
10 min read
Why Most Browser AI Demos Fail on Real Hardware
bruno_juca_7038c22bcca1db profile

Why Most Browser AI Demos Fail on Real Hardware

#ai #inference #hardware #benchmark
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.