DEV Community

#benchmark

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
A Benchmark Is Only as Honest as Its Harness
apppro_5726 profile

A Benchmark Is Only as Honest as Its Harness

#ai #benchmark #llm #testing
Comments
4 min read
Extraction APIs invented values for 17% of the fields that aren't in the document. Ours included.
velrimhq profile
Velrim

Extraction APIs invented values for 17% of the fields that aren't in the document. Ours included.

#ai #machinelearning #benchmark #llm
Comments
12 min read
A Small Transformer Trained in 1.5 Hours Beat Many LLMs on ARC
ajianaz profile

A Small Transformer Trained in 1.5 Hours Beat Many LLMs on ARC

#machinelearning #vectorsearch #quantization #benchmark
Comments
5 min read
Tried `sponsors/wonderwhy-er`: A Practical MCP Server Review
yan_cheng profile

Tried `sponsors/wonderwhy-er`: A Practical MCP Server Review

#ai #deepseek #machinelearning #benchmark
Comments
2 min read
Benchmark a Free AI Coding Tier on a Cold Server
apppro_5726 profile

Benchmark a Free AI Coding Tier on a Cold Server

#ai #benchmark #opensource #testing
Comments
4 min read
AxonASP vs. Native IIS ASP: Performance Benchmarks and Engine Architecture
lucas_guimaraes profile

AxonASP vs. Native IIS ASP: Performance Benchmarks and Engine Architecture

#iis #asp #vbscript #benchmark
Comments
2 min read
We ran 160 agent tasks across two frameworks. The frameworks tied. Then we changed the model.
benchclawio profile

We ran 160 agent tasks across two frameworks. The frameworks tied. Then we changed the model.

#python #ai #testing #benchmark
Comments
4 min read
A LongMemEval-S number you can reproduce
przemarzec profile

A LongMemEval-S number you can reproduce

#ai #agents #benchmark #python
Comments 4
6 min read
I Tested GLM-5.3-Flash and Qwen3.8-Flash on 24 Real Tasks
li_wujie_0995d9c1bca1f2e3 profile

I Tested GLM-5.3-Flash and Qwen3.8-Flash on 24 Real Tasks

#ai #llm #machinelearning #benchmark
Comments
6 min read
Twenty Prompts, One Compiler: A Free AI Server's Failure Matrix
datacpp_3670 profile

Twenty Prompts, One Compiler: A Free AI Server's Failure Matrix

#ai #cpp #testing #benchmark
Comments
5 min read
I Benchmarked Two Local LLMs on Real Dev Work — Qwopus 27B vs Muse Glimmer 30B
chpomob profile

I Benchmarked Two Local LLMs on Real Dev Work — Qwopus 27B vs Muse Glimmer 30B

#llm #ai #opensource #benchmark
Comments
5 min read
DeepSeek V4 Is Now the 'Kill Line' of AI Models — Here's What That Means
xiaomodern profile

DeepSeek V4 Is Now the 'Kill Line' of AI Models — Here's What That Means

#deepseek #ai #llm #benchmark
Comments
3 min read
Benchmarking AI Coding Agents on Real Pull Requests
donk8r profile

Benchmarking AI Coding Agents on Real Pull Requests

#ai #coding #benchmark #programming
Comments
7 min read
AI Daily Digest — August 1, 2026: ARC-AGI-3 Harness Discovery, EU AI Gigafactories, Devin SWE-1.7
hiroki-ii-ai profile

AI Daily Digest — August 1, 2026: ARC-AGI-3 Harness Discovery, EU AI Gigafactories, Devin SWE-1.7

#ai #agents #benchmark #hardware
Comments
7 min read
39,000 Torrents: The Bug My Green Benchmark Never Caught
ohugonnot profile

39,000 Torrents: The Bug My Green Benchmark Never Caught

#matching #algorithms #benchmark #selfhosting
1
Comments
8 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.