Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
benchmark
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
We recompute TypeSafe's 444x claim — here's what we found
chunxiaoxx
chunxiaoxx
chunxiaoxx
Follow
Sep 29
We recompute TypeSafe's 444x claim — here's what we found
#
ai
#
llm
#
benchmark
#
verification
Comments
Add Comment
1 min read
Verification as Protocol: We Test AI Agents' Memory — Our Grader Failed First
chunxiaoxx
chunxiaoxx
chunxiaoxx
Follow
Sep 29
Verification as Protocol: We Test AI Agents' Memory — Our Grader Failed First
#
ai
#
agents
#
benchmark
#
verification
Comments
Add Comment
1 min read
PQC-Bench Part 1 — measuring X25519MLKEM768 costs on a $0.04/hour Graviton3
asif naeem
asif naeem
asif naeem
Follow
Sep 28
PQC-Bench Part 1 — measuring X25519MLKEM768 costs on a $0.04/hour Graviton3
#
tls
#
security
#
aws
#
benchmark
Comments
1
 comment
5 min read
One Hung API Call Used to Kill My 1,000-Run Benchmark. Here's the Fix.
Debashish Ghosal
Debashish Ghosal
Debashish Ghosal
Follow
Sep 26
One Hung API Call Used to Kill My 1,000-Run Benchmark. Here's the Fix.
#
ai
#
llm
#
programming
#
benchmark
7
 reactions
Comments
Add Comment
3 min read
Claude Opus 5.5: 40% cheaper, frontier-grade performance
The Dev Signal
The Dev Signal
The Dev Signal
Follow
Sep 24
Claude Opus 5.5: 40% cheaper, frontier-grade performance
#
ai
#
devtools
#
programming
#
benchmark
Comments
Add Comment
5 min read
Glasshouse v0.1 Is Out: A Memory Benchmark for AI Systems
woochan
woochan
woochan
Follow
Sep 22
Glasshouse v0.1 Is Out: A Memory Benchmark for AI Systems
#
ai
#
memory
#
benchmark
#
wontopos
7
 reactions
Comments
1
 comment
2 min read
Onboarding benchmarks from real data across 464 SaaS products: median tour completion is 29%, 1-2 step tours complete at 73%, 9+ step tours at 8%
Olli
Olli
Olli
Follow
Sep 22
Onboarding benchmarks from real data across 464 SaaS products: median tour completion is 29%, 1-2 step tours complete at 73%, 9+ step tours at 8%
#
saas
#
onboarding
#
product
#
benchmark
Comments
1
 comment
2 min read
netcup VPS 1000 G12 benchmarked: how fast is it really?
serverkueche.de
serverkueche.de
serverkueche.de
Follow
Sep 20
netcup VPS 1000 G12 benchmarked: how fast is it really?
#
benchmark
#
vps
#
selfhosted
Comments
Add Comment
7 min read
Enterprise Vector Database 2026: Qdrant vs Milvus vs pgvector vs Pinecone
devrudals
devrudals
devrudals
Follow
Sep 19
Enterprise Vector Database 2026: Qdrant vs Milvus vs pgvector vs Pinecone
#
ai
#
devops
#
benchmark
#
cloud
Comments
Add Comment
23 min read
TypeSafe’s JEV Model: Is It Really 193x Faster and 444x Cheaper?
Ariful Islam
Ariful Islam
Ariful Islam
Follow
Sep 22
TypeSafe’s JEV Model: Is It Really 193x Faster and 444x Cheaper?
#
jev
#
typesafe
#
ai
#
benchmark
2
 reactions
Comments
1
 comment
6 min read
I Made a Memory Benchmark as Fair as I Could. 15 Stars, 0 Runs. What's Wrong With It?
woochan
woochan
woochan
Follow
Sep 28
I Made a Memory Benchmark as Fair as I Could. 15 Stars, 0 Runs. What's Wrong With It?
#
discuss
#
ai
#
benchmark
#
opensource
7
 reactions
Comments
4
 comments
2 min read
JetBrains Ranked AI Agents on Real Kotlin Projects. The Token Column Is the Real Story.
jamilxt
jamilxt
jamilxt
Follow
Sep 15
JetBrains Ranked AI Agents on Real Kotlin Projects. The Token Column Is the Real Story.
#
ai
#
kotlin
#
java
#
benchmark
1
 reaction
Comments
Add Comment
7 min read
AI Agent Evaluation End to End: How the LFORLA Drone Build Benchmark Scores Planning, Sourcing, and Assembly
RESK
RESK
RESK
Follow
Sep 28
AI Agent Evaluation End to End: How the LFORLA Drone Build Benchmark Scores Planning, Sourcing, and Assembly
#
ai
#
benchmark
#
agents
#
evaluation
2
 reactions
Comments
2
 comments
4 min read
How Fast Can Neovim Start? Benchmarking Popular Distros
glmlm
glmlm
glmlm
Follow
Sep 22
How Fast Can Neovim Start? Benchmarking Popular Distros
#
neovim
#
productivity
#
performance
#
benchmark
Comments
Add Comment
6 min read
Why I’m Building a New AI Memory Benchmark (And Why the Existing Ones Fall Short)
woochan
woochan
woochan
Follow
Sep 7
Why I’m Building a New AI Memory Benchmark (And Why the Existing Ones Fall Short)
#
ai
#
benchmark
#
startup
#
opensource
2
 reactions
Comments
Add Comment
2 min read
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account