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
13 Nov
Saebom Yoon
ICLayout-Bench scores only circuit layouts that pass checks
13 Nov
Jihwan Nam
Breaking
AI validation filters out harder language-model test items
13 Nov
Yejun Son
Breaking
Real-time maths checks improve reported reasoning accuracy
13 Nov
Yejun Son
Breaking
Google launches benchmark for visual document tasks
13 Nov
Daon Jeong
AI leaderboard separates accuracy from self-error detection
13 Nov
Chaewoo Lim
Breaking
OmniReview offers benchmark for reviewer recommendations
13 Nov
Chaewoo Lim
Kaggle winners put AI test design in focus
13 Nov
Chaewoo Lim
Breaking
Medical AI shows gap between recall and evidence use
10 Nov
Na Sunwoo
Scientific code AI routes repairs by failure type
10 Nov
Saebom Yoon
Breaking
Hybrid AI lacks evidence for 13.6% of police video events
10 Nov
Chaewoo Lim
TeViD compares two approaches to Turkish video fact-checking
10 Nov
Haeon Moon
Breaking
AISI releases benchmark for AI agent sandbox escapes
10 Nov
Haeon Moon
Breaking
AI models differ in continuing safety research sabotage
10 Nov
Jihwan Nam
Breaking
AI misinformation costs 3–169 times less to make than check
10 Nov
Yejun Son
Breaking
AI manufacturing models can run yet give wrong answers
10 Nov
Yejun Son
Breaking
DramaGrow reports accuracy gap between AI judging methods
10 Nov
Chaewoo Lim
Breaking
Study raises video AI object-counting accuracy to 65.0%
10 Nov
Gyeol Han
Breaking
Linear merging lifts Turkish model's maths score to 0.63
10 Nov
Gyeol Han
MCGI adjusts vector search effort to data geometry
10 Nov
Yejun Son
Extra layers give mixed gains in Vietnamese punctuation test
01
…
06
07
08
…
10