Verified, then logged.
Sun 22 Nov 2026 ·
01:14 KST
/ 16:14 UTC
한국어
|
EN
Search /
Home
AI
IT
Hardware
Policy
Contests
Showcase
Tag · Topic
Benchmarks
Articles and logged changes tagged Benchmarks.
189 in total
benchmark
14 Nov
Saebom Yoon
Breaking
MIGRO retains 99.9% of rebuilding quality after model switch
14 Nov
Chaewoo Lim
MOSS-Live trails GPT-Live-1 on multi-turn tasks
14 Nov
Gyeol Han
Weight deletion delivers gains on par with full fine-tuning
14 Nov
Seojin Ha
Meta releases e-means to speed up data clustering
14 Nov
Doyun Lee
Breaking
Image segmentation method finds look-alikes without training
14 Nov
Doyun Lee
Breaking
AFTER-WM adapts robot predictions without changing models
14 Nov
Haram Do
Breaking
PhysICL predicts physical fields without retraining
14 Nov
Gyeol Han
Breaking
PREWARN separates failure detection from early warning
14 Nov
Gyeol Han
Breaking
Classifier outperforms model at detecting perturbations
14 Nov
Dogyeom Baek
Breaking
NVIDIA adds faster double-precision matrix calculations
13 Nov
Doyun Lee
TKNP raises long-context AI throughput by up to 1.7 times
13 Nov
Doyun Lee
Breaking
AVCC adds human benchmark for next-speaker prediction
13 Nov
Na Sunwoo
Breaking
Alania-2 lowers word error rate in Turkish speech synthesis
13 Nov
Na Sunwoo
Breaking
ElevenLabs raises Dutch identity-check accuracy to 90%
13 Nov
Saebom Yoon
Breaking
B3 speeds up self-editing diffusion language models
13 Nov
Chaewoo Lim
Breaking
AI video detectors miss most fakes after reposting
13 Nov
Na Sunwoo
Breaking
AI benchmark tests nonverbal reasoning in early childhood
13 Nov
Yejun Son
Breaking
LIS claims safety alignment gains with a smaller dataset
13 Nov
Daon Jeong
Multi-word training cuts English tokens; model tests remain
13 Nov
Doyun Lee
Breaking
Legal AI training method balances reasoning and answers
01
…
04
05
06
…
10