ByteDance-Seed Releases EdgeBench for Text Generation
ByteDance-Seed · hf · 2026-07-06
The ByteDance-Seed team has released the EdgeBench dataset on Hugging Face, currently trending on the leaderboard. Designed for text generation tasks, the dataset is released under the CC BY 4.0 license, stored in JSON format, and contains fewer than 1K samples. It supports loading via mainstream libraries like datasets, pandas, polars, and mlcroissant. EdgeBench is likely intended for benchmarking the performance of edge or lightweight language models.
More from Research
- NUS builds a soft force sensor that drives actuators without electronics or power — CurieuxExplorer · 2026-07-27
- Chelsea Finn says robot RL is bottlenecked by physical rollout cost, not algorithms — ycombinator · 2026-07-27
- ICML 2026 oral paper replication scores stay middling after a stricter re-scoring — profjamesevans · 2026-07-27
- Long-running agents will need immutable event logs, this thread argues — sebpaquet · 2026-07-27
- Seed IQ navigates Doom II, prompting questions about benchmarks beyond ARC-AGI — Fit_Transition8824 · 2026-07-27
- Agentic Data Science in Practice: Agents Write Code but Answer Wrong Questions — hugobowne · 2026-07-27