Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
benchmark
Follow
Hide
Posts
Left menu
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Which Gemini Model Should You Use? Neon, Argon, Hydrogen, Carbon, Flash or Gemma. It Depends.
xbill
xbill
xbill
Follow
for
Google Developer Experts
Nov 19
Which Gemini Model Should You Use? Neon, Argon, Hydrogen, Carbon, Flash or Gemma. It Depends.
#
gemini
#
gemma
#
benchmark
#
ai
7
reactions
Comments
Add Comment
10 min read
Moderation
Thinking On or Off? Gemma 4 E4B on an 8 GB RTX 3050
xbill
xbill
xbill
Follow
for
Google Developer Experts
Nov 19
Thinking On or Off? Gemma 4 E4B on an 8 GB RTX 3050
#
gemma
#
llm
#
benchmark
#
ai
10
reactions
Comments
1
comment
9 min read
Moderation
Qwen3.5-9B on RTX 5060 Ti: 260k tokens of context in 16 GB
Hyperbolic
Hyperbolic
Hyperbolic
Follow
Nov 19
Qwen3.5-9B on RTX 5060 Ti: 260k tokens of context in 16 GB
#
ai
#
llm
#
benchmark
#
devops
Comments
Add Comment
4 min read
Moderation
IFBench on Hugging Face: 0 of 23 Rows Are Verified, and Ranks 1 to 6 Sit Inside One 300-Prompt Error Band
Ward Ed
Ward Ed
Ward Ed
Follow
Nov 19
IFBench on Hugging Face: 0 of 23 Rows Are Verified, and Ranks 1 to 6 Sit Inside One 300-Prompt Error Band
#
ai
#
machinelearning
#
llm
#
benchmark
Comments
Add Comment
10 min read
Moderation
How accurate is Google Maps' Ask Maps? It scored 49/100 on PlaceBench
VOYGR
VOYGR
VOYGR
Follow
Nov 19
How accurate is Google Maps' Ask Maps? It scored 49/100 on PlaceBench
#
ai
#
maps
#
benchmark
#
google
Comments
Add Comment
2 min read
Moderation
DeepSWE on Hugging Face: Rank 1 Is an Agent Layer 21 Points Above Its Base Model, and 22 of 34 Rows Name No Scaffold
Ward Ed
Ward Ed
Ward Ed
Follow
Nov 18
DeepSWE on Hugging Face: Rank 1 Is an Agent Layer 21 Points Above Its Base Model, and 22 of 34 Rows Name No Scaffold
#
ai
#
machinelearning
#
benchmark
#
llm
1
reaction
Comments
Add Comment
14 min read
Moderation
PlaceBench: we tested six AI assistants on 150 questions about real places
VOYGR
VOYGR
VOYGR
Follow
Nov 18
PlaceBench: we tested six AI assistants on 150 questions about real places
#
ai
#
llm
#
benchmark
#
maps
Comments
Add Comment
3 min read
Moderation
El diario económico coreano Maeil Business cuenta 12 primeros puestos de Darwin en Hugging Face: cuéntalos tú con Python
김민식/학생
김민식/학생
김민식/학생
Follow
Nov 18
El diario económico coreano Maeil Business cuenta 12 primeros puestos de Darwin en Hugging Face: cuéntalos tú con Python
#
ai
#
opensource
#
huggingface
#
benchmark
Comments
Add Comment
8 min read
Moderation
매일경제가 정리한 허깅페이스 공인 벤치마크 지도: 리더보드 57개 중 Darwin이 12개에서 1위, 같은 숫자를 API로 직접 세어 봤습니다
Vidraft_lab
Vidraft_lab
Vidraft_lab
Follow
Nov 18
매일경제가 정리한 허깅페이스 공인 벤치마크 지도: 리더보드 57개 중 Darwin이 12개에서 1위, 같은 숫자를 API로 직접 세어 봤습니다
#
ai
#
opensource
#
huggingface
#
benchmark
Comments
Add Comment
4 min read
Moderation
Turning 12 benchmark write-ups into a citable dataset (with a DOI) in one afternoon
Xplormity
Xplormity
Xplormity
Follow
Nov 17
Turning 12 benchmark write-ups into a citable dataset (with a DOI) in one afternoon
#
datascience
#
opendata
#
machinelearning
#
benchmark
Comments
Add Comment
3 min read
Moderation
plain 0.5.0 against forge 1.9.0 on PRBMath, Solady and Morpho Blue: what ran and how long it took
borodutch.eth 💎🤲
borodutch.eth 💎🤲
borodutch.eth 💎🤲
Follow
Nov 17
plain 0.5.0 against forge 1.9.0 on PRBMath, Solady and Morpho Blue: what ran and how long it took
#
solidity
#
ethereum
#
foundry
#
benchmark
Comments
Add Comment
5 min read
Moderation
Parakeet vs. Whisper on an AMD iGPU: a speech-to-text benchmark on Linux
Asher Buk
Asher Buk
Asher Buk
Follow
Nov 16
Parakeet vs. Whisper on an AMD iGPU: a speech-to-text benchmark on Linux
#
linux
#
ai
#
opensource
#
benchmark
1
reaction
Comments
Add Comment
5 min read
Moderation
qwen3.5-4b on a 16 GB RTX 5060 Ti: 823 tokens per second for 16 users
Hyperbolic
Hyperbolic
Hyperbolic
Follow
Nov 16
qwen3.5-4b on a 16 GB RTX 5060 Ti: 823 tokens per second for 16 users
#
ai
#
llm
#
benchmark
#
devops
Comments
1
comment
4 min read
Moderation
The 29GB that didn't add up in my Edge0-145B vs Opus video
InApp
InApp
InApp
Follow
Nov 16
The 29GB that didn't add up in my Edge0-145B vs Opus video
#
llm
#
benchmark
#
vram
#
ai
1
reaction
Comments
Add Comment
1 min read
Moderation
Is there an independent benchmark of web search APIs like Tavily, Exa and Brave?
Ricardo Batista
Ricardo Batista
Ricardo Batista
Follow
for
cloro
Nov 15
Is there an independent benchmark of web search APIs like Tavily, Exa and Brave?
#
ai
#
agents
#
search
#
benchmark
Comments
Add Comment
7 min read
Moderation
👋
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