Explore Data on 5000 Model-Benchmark Pairs Showing AI Regressions
gleech · x · 2026-08-27
The author released the full dataset containing 5,000 model-model-benchmark triplets, illustrating performance fluctuations across AI benchmark versions.
More from Research
- Google Intrinsic's 3PT unifies detection, segmentation and 6DoF pose, wins both BOP 2025 tracks — kscottz · 2026-08-27
- Thom Wolf Unveils Microduck, a 25cm Open-Source RL-Trained Biped Robot — mervenoyann · 2026-08-27
- Prediction: Robotics to be Solved via RL from Scratch Using Simulators — yacineMTB · 2026-08-27
- BaguanHR pushes limits of high-res weather forecasting via data scaling — NJUHMLAI · 2026-08-27
- AI detects pancreatic cancer up to 3 years before clinical diagnosis — EricTopol · 2026-08-27
- Vector Database by Hand: A 10-Step Walkthrough of RAG Mechanics — ProfTomYeh · 2026-08-27