Verified, then logged.
Sun 22 Nov 2026 ·
01:04 KST
/ 16:04 UTC
한국어
|
EN
Search /
Home
AI
IT
Hardware
Policy
Contests
Showcase
Tag · Topic
Benchmarks
Articles and logged changes tagged Benchmarks.
189 in total
benchmark
10 Nov
Saebom Yoon
RoleWalk embeds one million graph nodes on a single CPU core
10 Nov
Gyeol Han
Skill at editing AI weights concentrates in a few new models
10 Nov
Sian Ryu
Ant's Ling-3.2-flash tops Claude Opus 5 in visual benchmarks
10 Nov
Doyun Lee
GeoJeV trades 1.12 extra seconds for 5.32 points of accuracy
10 Nov
Doyun Lee
MINE lifts Llama 3.1 8B inference speed 2.52x on RTX 4060 Ti
10 Nov
Doyun Lee
Khmer benchmark drops LLM judges but still needs LLM answers
10 Nov
Minjae Cha
Nvidia unveils VFlash, claiming 5x faster robot AI inference
10 Nov
Saebom Yoon
Peer signals reduce LLM public accuracy by up to 47.8 points
10 Nov
Jihwan Nam
Denoising audio before speaker embeddings raises error rates
10 Nov
Jihwan Nam
Shapley benchmark finds standard metrics differ on real data
10 Nov
Jihwan Nam
20 Atari games expose vision AI's limits in following motion
10 Nov
Haram Do
ML benchmark for chaotic three-body orbits publishes dataset
10 Nov
Gyeol Han
KLEAR holds knowledge fixed to test Korean LLMs' application
10 Nov
Gyeol Han
GPT-6 Astra gains 22.9 points on OpenAI's life sciences test
10 Nov
Jihwan Nam
NAVER Cloud's multimodal training throughput rises to 150.2%
8 Nov
Gyeol Han
Breaking
llama-modchip fits 284B DeepSeek model into 64GB RAM, no GPU
7 Nov
Gyeol Han
METR estimates 1.9x faster benchmark progress at Anthropic
7 Nov
Gyeol Han
Breaking
Baidu opens ERNIE 5.5 Flash Base weights, but not for Korea
6 Nov
Gyeol Han
Breaking
More dreaming lifts Claude's wiki quiz score from 13% to 48%
5 Nov
Taeoh Kwon
Breaking
Rubin adds about 3% HBM per GPU, up to 30x output per dollar
01
…
07
08
09
10