35B Beats 1.6T: BigBang Model Achieves SOTA via Self-Evolving Synthetic Data
ChengleiSi · x · 2026-08-07
The research team introduced BigBang-V1, based on Qwen3.6-35B-A3B. Post-trained entirely on synthetic data, it outperforms the 1.6T parameter DeepSeek V4 Pro Preview on four frontier benchmarks.
The core breakthrough lies in data-layer Recursive Self-Improvement (RSI): the AI autonomously rewrites its data-generation code, using real-world gains to steer subsequent generations. Grounded in verifiable frontier tasks, this method utilizes a generator-critic loop to continuously expose capability gaps and produce high-quality data, achieving SOTA performance at a fraction of the scale.
Related event: BigBang-V1: 35B Model Beats 1.6T Parameter Giants(3 posts)→
More from Models
- Opus 5.5 turns heads with surprisingly polished vertical video demo — FinanceYF5 · 2026-10-16
- Astra 6.1 may arrive before end of month, reads dev's 'we are cooking' tease — haider1 · 2026-10-16
- Open-source OCR model indra-ocr trends on Hugging Face with CPU support — datalab-to · 2026-10-16
- Xiaohongshu's Vela 35B turns anonymized user behavior into supervision, gains +11.5 on VelaBench — AdinaYakup · 2026-10-16
- KOL: No better model than Anthropic's Opus right now, its magic is back — kimmonismus · 2026-10-16
- Users blast Gemini in Chrome's 'draconian' usage caps: memory costs 2-4% per use — North-American · 2026-10-16