Verified, then logged.
Sun 22 Nov 2026 ·
00:27 KST
/ 15:27 UTC
한국어
|
EN
Search /
Home
AI
IT
Hardware
Policy
Contests
Showcase
Tag · Topic
Benchmarks
Articles and logged changes tagged Benchmarks.
189 in total
benchmark
22 Nov
Chaewoo Lim
Breaking
Higgsfield compares 8-second clips made from a single prompt
21 Nov
Doyun Lee
VidToC compares video token compression across three tasks
21 Nov
Doyun Lee
Breaking
Contrastive learning improves AI jailbreak detection
21 Nov
Jihwan Nam
Breaking
DOCK solves 15 robot object placement tasks in a simulation
21 Nov
Jihwan Nam
E-prop posts 100% survival in a humanoid robot walking trial
21 Nov
Haram Do
Physical AI series examines conditions in simulation testing
21 Nov
Yejun Son
Breaking
Stored abstracts lift ranking score in paper discovery test
21 Nov
Doyun Lee
Breaking
MORSEPose learns to estimate pose without surface models
21 Nov
Na Sunwoo
Breaking
Speech recognition model tags breaths in transcripts
21 Nov
Na Sunwoo
Breaking
AI model outputs first speech audio in 390 ms on NVIDIA GB10
21 Nov
Na Sunwoo
Breaking
Compressed translation models take up to 5.3 times as long
21 Nov
Minjae Cha
CaDO automates answer repair in causal reasoning datasets
21 Nov
Saebom Yoon
Breaking
STAGE identifies causal links across disaster posts
21 Nov
Jihwan Nam
Breaking
KIWI-EP cuts the time vLLM takes to generate an output token
21 Nov
Haram Do
Breaking
Joint model detects more errors in first-person video
21 Nov
Yejun Son
Breaking
Models vary in reading context in English and Mandarin tests
21 Nov
Chaewoo Lim
ElevenLabs unveils speech recognition models for two uses
21 Nov
Gyeol Han
Breaking
Single-pass model gets 46.0% on medical multiple-choice test
21 Nov
Gyeol Han
Study tests language model weight repair without retraining
21 Nov
Yejun Son
NeuroFusion’s Cerefin ranks first overall on ForecastBench
01
02
03
…
10