OpenJev Benchmark Reworked: Accuracy Weighted Higher, Probability Calibration Added
airesearch12 · x · 2026-09-19
The openjev benchmark author revised his earlier equal-weight scheme, tilting scoring toward accuracy since a dirt-cheap but wildly inaccurate model is trivial to build. He also plans to add a new axis: accuracy on probabilities, i.e. calibration. The design is still a work in progress.
Related event: Nearly 20 openjev models emerge as enthusiast launches leaderboard(4 posts)→
More from Research
- Gradient-free weight editing cuts VLM FigStep attack success from 49% to 2% — lateinteraction · 2026-11-04
- Anthropic says it may imminently hit RSP threshold for AI-accelerated R&D, releases provable inference work — tobyordoxford · 2026-11-04
- Google scanned 1,033 real household products, packed into a 345 MB GLB for three.js — victormustar · 2026-11-04
- These 10 GPU optimization papers are why your model runs fast today — NandoDF · 2026-11-04
- INT8 isn't the problem: I benchmarked samplers on INT8 flow models — YakovSava · 2026-11-04
- Karpathy Boosts Open Hacker News Dataset: 10M+ Posts Usable as a Personal Knowledge Base — huangyun_122 · 2026-11-04